3D Visual Question Answering

Also known as VQA

Ask about this topic

Overview

Three-dimensional visual question answering (VQA) asks models to answer questions that require understanding objects, layouts, distances, viewpoints, or events in 3D scenes and volumes. Systems combine language models with point clouds, RGB-D images, multiview video, or reconstructed scene representations such as occupancy maps and scene graphs; some also use geometric tools to measure or retrieve relevant evidence. Benchmarks such as ScanQA and SQA3D test scene understanding and spatial reasoning, while medical VQA evaluates reasoning over volumetric scans. A central challenge is ensuring answers are grounded in 3D evidence rather than language or visual shortcuts, while making reasoning over many views accurate and efficient.

Latest papers

CardsList

51 papers9 papers in the last four weeks, up 50% on the four weeks before. 0.1% of all new papers.

Oct 27, 2026

Zhengrong-Spatial-Aware 1.0: Advancing 3D Multimodal Intelligence

This report presents the implementation and validation of two end-to-end multimodal adaptation pipelines for 3D-aware visual question answering on a custom spatial dataset. The first pipeline fine-tunes HiSpatial-3B, which augments RGB observations with metric-scale 3D point maps; the second adapts Qwen3-VL through memory-efficient QLoRA-based supervised fine-tuning. The completed engineering stack covers dataset conversion, image-annotation alignment, monocular geometry preprocessing, instruction construction, mixed-domain training, checkpoint management, batch inference, and automated evaluation. On the target spatial benchmark, HiSpatial adaptation increases overall accuracy from 1.73% before fine-tuning to 79.89% at 3,600 steps. On a separately collected styled split, accuracy improves from 14.9% to 55.1%, indicating transfer beyond the original training set. The Qwen3-VL pipeline is likewise implemented end-to-end for both 8B- and 32B-scale models using mixed-domain QLoRA adaptation. The resulting accuracy improves from 20.74% to 45.27% for Qwen3-VL-8B and from 30.79% to 47.60% for Qwen3-VL-32B. Together, these results establish two complementary and reproducible adaptation pipelines for geometry-aware and general-purpose multimodal spatial reasoning. These results establish a reproducible engineering foundation for subsequent work on metric 3D reasoning, spatial grounding, and domain-adapted multimodal systems, while also identifying training-data composition as a central factor in preserving general multimodal capability during specialization.

Yu Zhang, Xiaogang Wang, Yuhang Cheng +2

Beijing Freedo Technology Co., Ltd. · Southwest University

3D Visual Question AnsweringMultimodal Spatial Reasoning3D VLMsMultimodal Large Language Models
AskPDF
Oct 27, 2026

3D-SceneQ: Empowering 3D LLM With Query-Guided Adaptive Pruning and Multi-Modal Feature Enhancement

Current 3D scene understanding pipelines typically concatenate vast numbers of 3D object tokens with text tokens and feed the resulting sequence to a Large Language Model (LLM). However, existing 3D-LLMs for scene understanding encounter two major limitations: (i) excessive inclusion of task-irrelevant object data, introducing noise that reduces reasoning accuracy and increases hallucinations; and (ii) reliance solely on point cloud data, which inherently lacks the rich semantic information available in complementary 2D modalities, such as color, material properties, texture, and high-level contextual relationships. To address these challenges, we introduce 3D-SceneQ, a 3D LLM that unifies adaptive token pruning with multimodal semantic enrichment, markedly advancing scene understanding, reasoning, and grounding. Specifically, we propose a Query-Guided Adaptive Pruning (QGAP) module that adaptively selects task-relevant objects based on the intended meaning of user instructions, leveraging a learnable latent query to retain critical information while effectively suppressing irrelevant noise. In addition, we introduce a Multi-modal Object-level Feature Enhancement (MOFE) module, which integrates 2D feature embeddings from pre-trained models into 3D representation to enrich object-level semantic information. Evaluations show that 3D-SceneQ outperforms current state-of-the-art methods across multiple benchmarks (e.g., +5.7 CIDEr on Scan2Cap and +17.0 EM@1 on SQA3D), demonstrating its remarkable capabilities in various 3D language reasoning tasks.

Yongqi Shan, Lu Zhang, Jiazuo Yu +2

School of Artificial Intelligence, Dalian University of Technology, Dalian 116081, China. · School of Information and Communication Engineering, Dalian University of Technology, Dalian 116081, China.

3D Scene Understanding3D VLMsToken Pruning3D Visual Question AnsweringMultimodal Fusion3D Visual Grounding
AskPDF
Oct 26, 2026

TP-JSCC: Efficient Token Pruning and Joint Source-Channel Coding for LVLMs-based 3D-VQA in Cloud-Edge Collaboration

Deploying large vision-language models (LVLMs) on resource-constrained embodied agents for 3D visual question answering necessitates cloud-edge collaboration. However, offloading massive visual data to the cloud over bandwidth-limited and noisy channels introduces severe latency and transmission distortion. To address this, we propose TP-JSCC, an efficient token pruning and joint source-channel coding method for LVLMs-based 3D-VQA in Cloud-Edge Collaboration. First, we develop a Local and Global Semantics-based Hybrid Token Pruning (LGS-HTP) module to significantly reduce the visual token count. By decoupling foreground-background tokens and jointly selecting local and global semantics, LGS-HTP effectively reduces redundancy while preserving reasoning-critical tokens. Second, we introduce a lightweight Token Joint Source-Channel Coding (T-JSCC) module to further compress the pruned tokens and ensure their robust transmission over error-prone channels. By employing lightweight cascaded linear layers and Signal-to-Noise Ratio (SNR)-adaptive mechanism, this module adapts to fluctuating channel conditions while maintaining minimal computational overhead. Extensive experiments on ScanQA and SQA3D datasets indicate the exceptional efficiency and robustness of our approach. Specifically, on ScanQA validation set, the LGS-HTP module could achieve 90% pruning ratio while incurring less than a 1% CIDEr loss. Building on this, the T-JSCC further compresses the tokens by 18 times, resulting in an overall 180 times data volume reduction for robust transmission, while saving 90% in computational complexity for LVLM deployment. Our code is available at https://github.com/yuanhui0325/TP-JSCC.

Zhengxin Li, Chongzhen Tian, Hui Yuan +2

School of Control Science and Engineering, Shandong University, Jinan 250061, China · Key Laboratory of Machine Intelligence and System Control, Ministry of Education, Jinan 250061, China · Shandong Key Laboratory of Intelligent Communication and Sensing-Computing Integration, Jinan 250100, China +2

Visual Token Compression3D Visual Question AnsweringJoint Source-Channel CodingVisual Token Pruning3D VLMs
AskPDF
Oct 20, 2026

P3^3-VLM: A Point-based Alternative for Grounded 3D Vision-Language Models

Examining existing benchmarks for grounding in 3D VLMs reveals a pervasive "semantic leakage" in the evaluation and prompting protocols: a heavy reliance on bounding boxes as spatial prompts or representation primitives. Because bounding boxes are highly informative of object categories, they introduce a shortcut for the models to neglect visual information during 3D VLM training. We demonstrate this with a "blind" LLM that, prompted only with the box coordinates, can perform surprisingly well. To further analyze this shortcut, we propose point-based grounding prompting - querying models with a single 3D point instead of a box. Under this protocol, the accuracy of the blind LLM drops from 36.4% to 18.0% on ScanNet's Nr3D, and similarly degrades for 3D VLMs (e.g. LL3DA). Building on this insight, we introduce P3^3-VLM, a novel tri-pathway 3D VLM that supports point-based prompts and achieves 52.1% state-of-the-art accuracy on location-grounded captioning under this setting. To achieve this, we redesign the architecture while keeping it detector-free, scene-centric, and suitable for 3D GS inputs. P3^3-VLM utilizes three complementary pathways (location-, task-, and context-aware), enabling strong reasoning about scenes without any bounding box dependencies. The key benefit of point-based learning is a consistent improvement across settings: P3^3-VLM achieves state-of-the-art performance under point-based grounding while also improving robustness, OOD generalization, and performance on ungrounded scene-centric 3D VQA benchmarks, reflecting its reduced reliance on bounding-box shortcuts and resulting stronger visual-spatial reasoning.

Anna-Maria Halacheva, Jan-Nico Zaech, Sombit Dey +2

INSAIT, Sofia University “St. Kliment Ohridski”

3D VLMs3D Visual GroundingShortcut Learning3D Visual Question Answering
AskPDF
Oct 17, 2026

Do 3D Large Language Models Really Use 3D Evidence?

Recent 3D Large Language Models (3D-LLMs) have shown strong performance on scene question answering with extensive post-training. Yet, existing benchmarks rarely evaluate how 3D-LLMs respond to referential ambiguity, insufficient scene evidence, or false presuppositions, obscuring whether their responses are grounded in 3D evidence. In this work, we introduce UNICORNS, a benchmark for evaluating the reliability of 3D-LLM responses across four evidence conditions. UNICORNS contains 11,387 questions across 557 ScanNet scans, covering eight challenge categories alongside answerable controls. A response passes only if it satisfies the required response behavior and contains no scene claim unsupported by the available evidence. Evaluation of six open-sourced 3D-LLMs reveals a pronounced performance gap: even the strongest zero-shot model achieves 61.22% accuracy on answerable controls, but only 40.94% across the eight challenge categories. To address this gap, we further propose HORN, an obligation-aware post-training method combining group-relative task rewards, leaf-conditioned obligation rewards, and supervised control replay. Extensive experiments demonstrate that HORN reaches 75.1±1.0%75.1 \pm 1.0\% across the challenge categories and 77.2±0.8%77.2 \pm 0.8\% overall, outperforming all baselines without degrading answerable-control accuracy. Our findings enable a systematic evaluation and improvement of evidence-grounded 3D reasoning for 3D-LLMs (code: https://anonymous.4open.science/r/unicorns-6B38/).

Yifei Zhao, Fanyu Zhao, Han Zhang +6

Fudan University · University of Science and Technology of China

3D VLMs3D Visual Question Answering3D Visual Grounding
AskPDF
Oct 15, 2026

Learning to Think and Explore in 3D World

We study how vision-language models (VLMs) can learn to think and actively explore in 3D space. Instead of providing multi-view images, videos, or 3D representations to the model, we preserve the native visual encoding of VLMs, i.e., a single image, one at a time, just like humans, and treat the 3D representation only as an environment with which the model can interact through actions (e.g., move left) and observations (rendered images). Each rollout begins from an initial first-person view and a visual question. The model can then iteratively reason, navigate, and reorient its viewpoint before committing to a final answer. Following an initial trajectory-supervised finetuning, we apply reinforcement learning (RL) with rewards driven primarily by final-answer correctness. Crucially, RL provides no direct supervision over which viewpoints the model should visit or which exploration actions it should take. Instead, the model must learn an effective exploration policy solely from the extent to which its interactions improve performance. Across six 3D benchmarks, our model ACT3D achieves an average accuracy of 53.2% that improves its base Qwen model by 22.0% and surpasses proprietary Gemini 3.6 Flash. ACT3D also outperforms existing open-source 3D methods while using 50-70% fewer input frames, and generalizes to unseen domains with an average improvement of 5.9% over its supervised initialization. Further analysis reveals adaptive, question-conditioned exploration. Performance gains over the base model increase from 0.6% on questions answerable from the initial view to 16.3% on those requiring extensive exploration. ACT3D searches for occluded targets, avoids unnecessary exploration, and acquires complementary viewpoints for spatial comparisons. These findings demonstrate that outcome-based RL enables VLMs not only to reason over visual evidence, but also to learn when and how to acquire it.

Yijiang Li, Bingyang Wang, Nuno Vasconcelos

University of California San Diego · Georgia Institute of Technology

VLM Reasoning3D Visual Question AnsweringActive Visual PerceptionRL for VLMs
AskPDF
Oct 14, 2026

Holi-Spatial 360: Generative Reconstruction from Sparse Panoramas for Spatial Rendering and Intelligence

Spatial intelligence requires scalable 3D environments that are both photorealistic and semantically grounded, yet existing indoor datasets are dominated by room-scale captures and costly LiDAR acquisition. Online real-estate platforms offer abundant panoramas of diverse multi-room homes, but sparse viewpoints and texture-poor regions make reconstruction severely under-constrained. We introduce Holi-Spatial 360, a generative reconstruction and data curation framework for converting these panoramas into annotated multi-room 3D environments. Because reconstruction quality bounds subsequent generation, our Correspondence-Guided Geometric Optimization converts feed-forward reconstruction priors into reliable cross-view constraints and builds a coherent 3D Gaussian Splatting representation as 3D spatial memory. Adapted single-image and video priors then restore appearance and complete continuous trajectories while preserving observed content. The reconstructed scenes support arbitrary RGB-D rendering and an automated curation pipeline that combines end-to-end 3D grounding with VLM-based verification. Holi360 contains over 1K multi-room 3DGS scenes, more than 100K instance annotations, and 2M spatial question-answer pairs. We also introduce the Holi360 benchmark to evaluate the spatial understanding of VLMs in real-world, multi-room indoor environments. Experiments demonstrate superior reconstruction and curation quality under sparse panoramic inputs, while fine-tuning VLMs on Holi360 substantially improves spatial reasoning capabilities.

Yuanyuan Gao, Zhirui Liu, Yuning Gong +9

The Hong Kong University of Science and Technology · ShanghaiTech University · Tencent +4

Indoor Scene ReconstructionPanoramic 3D Reconstruction3D Scene Understanding3D Gaussian Splatting3D Visual Question Answering
AskPDF
Oct 12, 2026

EgoAlign: Situated 3D Understanding without Situation Descriptions

Situated 3D Question Answering requires models to interpret a 3D scene relative to an agent's pose. Existing methods commonly convey that pose through a natural-language situation description, which may be unavailable or costly to obtain in real-world deployments. While some methods additionally incorporate numerical pose, we find that randomly shuffling the agent pose causes little performance degradation, indicating limited functional dependence on the numerical pose. To address this gap, we introduce EgoAlign, a simple 3D language model that represents a scene in an agent-centric coordinate frame, together with a dedicated egocentric alignment stage comprising four complementary tasks: object category recognition, egocentric direction prediction, metric distance estimation, and spatial relation prediction. This stage teaches the model to consistently interpret scene geometry relative to the agent's pose before task-specific fine-tuning. EgoAlign achieves the strongest performance on SQA3D, Real-3DQA, and MSQA among compared methods while remaining highly efficient. More importantly, removing textual situation descriptions yields comparable or better downstream performance, whereas shuffling EgoAlign's numerical pose causes substantial degradation. These results show that EgoAlign establishes agent-centric spatial context directly from numerical pose without requiring textual situation descriptions.

Yiyang Li, Tianyi Ma, Zehong Wang +1

Department of Computer Science and Engineering, University of Notre Dame

3D Visual Question Answering3D VLMs3D Scene Representation
AskPDF
Oct 5, 2026

Lens3D: Target-Conditioned Visual Foveation for Fine-Grained 3D Understanding

Existing 3D large language models often overlook fine-grained attributes and less visually salient objects and parts, even when relevant evidence is present in scene videos. We introduce Lens3D to improve fine-grained object understanding through external visual assistance and knowledge transfer. Its LensUnd pipeline adopts 3D localization to select informative, complementary views for an external 2D vision-language model, supporting fine-grained object captioning, small-object grounding, and fine-grained object question answering. LensDistill transfers the resulting fine-grained knowledge to 3D LLMs through detailed caption supervision, enabling captioning from native inputs without external VLM calls. We also construct LensBench, a held-out evaluation set of 2,068 objects with three silver-standard reference descriptions per object. Experiments with Video-3D LLM and 3DRS demonstrate that LensDistill substantially improves fine-grained object captioning while preserving existing grounding and scene-level QA performance. These results establish the feasibility of transferring externally acquired fine-grained knowledge into native 3D LLMs.

Junming Huang, Zini Chen, Shuaiying Hou +3

Zhejiang University · LIGHTSPEED

Active View Selection3D Visual Question Answering3D VLMs3D Visual Grounding
AskPDF
Oct 4, 2026

Render to Reason: Novel-View Semantic Prediction Improves Spatial Understanding in VLMs

Recent works augment Vision-Language Models with geometry features from pretrained 3D models, expecting that the geometric signal will boost spatial reasoning. However, we find that simply fusing geometry features and training on standard spatial QA yields only marginal improvements on high-level multi-hop tasks. We attribute this gap to a training-signal problem: standard spatial QA can be largely answered from visual features and language priors, so the geometry pathway receives weak gradients and fails to integrate with the visual features. To provide a training signal that requires geometry, we propose novel-view semantic rendering as an auxiliary training task that requires the model to predict the semantic layout of an unobserved viewpoint, inspired by humans' ability to mentally simulate novel viewpoints during spatial reasoning. This task encourages joint use of both pathways: geometry provides pose-dependent visibility, while vision provides semantic content. Our auxiliary task yields consistent improvements over the geometry-augmented baseline across all three benchmarks (up to +1.6 on VSI-Bench, +2.2 on ReVSI, +2.9 on our 3D-Point-QA dataset) and our full model surpasses prior open-source methods on VSI-Bench and on ReVSI. Project page: https://yuqunw.github.io/Render2Reason/.

Yuqun Wu, Yao Xiao, Chuhang Zou +2

University of Illinois at Urbana-Champaign · Meta

Visual Spatial Reasoning3D Visual Question Answering3D VLMs
AskPDF
Sep 29, 2026

Exemplar2VQA: A Scalable Exemplar-Driven Visual Question Answering Generation Framework via Multi-Agent Coding

Advancing spatial intelligence in Multimodal Large Language Models (MLLMs) is bottlenecked by the scarcity of complex, scalable 3D question-answer (QA) data. While manual annotation is labor-intensive, directly utilizing LLMs to synthesize these QA pairs often fails due to their inherent deficiencies in spatial and geometric computation. We introduce Exemplar2VQA, a scalable exemplar-driven visual question answering generation framework that rapidly synthesizes large-scale spatial QA pairs in simulated environments via multi-agent coding. By equipping collaborative agents with a meticulously designed library of geometric utilities, Exemplar2VQA bypasses LLMs' spatial reasoning flaws through deterministic code execution. Crucially, the framework exhibits remarkable versatility: taking diverse static object-centric spatial query templates as exemplars, it seamlessly and autonomously scales them into massive, high-fidelity synthetic datasets. Fine-tuning Qwen2.5-VL (3B/7B) exclusively on Exemplar2VQA-generated synthetic indoor data yields significant performance improvements across various diverse benchmarks. Furthermore, its effectiveness is not limited to in-domain indoor datasets but also robustly extends to outdoor and mixed-scene benchmarks. These results establish Exemplar2VQA as a scalable and powerful paradigm for bridging the sim-to-real gap in Embodied AI. Our code is at https://github.com/yingjiayu12/Exemplar2VQA

Jiayu Ying, Qijian Tian, Ruijie Xu +4

East China Normal University · Shanghai Jiao Tong University · Fudan University +1

Visual Question AnsweringMultimodal Large Language ModelsSynthetic Data Generation for Robotics3D Visual Question Answering
AskPDF
Sep 28, 2026

Long Time No See: Benchmarking VLMs for Out-of-Sight Spatiotemporal Reasoning in Egocentric Videos

Real-world AI systems must reason about objects that are no longer visible: an AR assistant guiding a user back to an object used earlier, a household robot retrieving an item someone put away. This requires not just recalling where an object was last seen, but updating its state when it is moved and retaining that update once it leaves view. We refer to this as out-of-sight spatiotemporal reasoning. We introduce Beyond3D, the first VQA benchmark to isolate this ability in dynamic egocentric video: every query targets an object that has been relocated and has since left the field of view. We create our questions from HD-EPIC annotations, building a visibility track for each dynamic object from its 3D position, the camera pose, and the scene geometry to understand at each moment whether it is visible, occluded, or out of view. Beyond3D comprises 9,000 questions in eight types over 135 videos from nine participants, organized as one reasoning chain: visual grounding (is the target observable now), temporal grounding (when it was last visible and last placed), scene localization (which fixture anchors that location), and 3D spatial perception (where it lies relative to the current viewpoint or another object in the scene). We benchmark nine general-purpose and spatially specialized VLMs. The best model reaches 42.2% against 29.7% chance and text-only baselines reaching 31.9%, with the largest failures in recovering when an object was last visible, showing that tracking object movement out of sight remains far from solved for current VLMs.

Fangzhou Ma, Ivo Alexander Ban, Eren Homburg +5

ETH Zurich · Microsoft Spatial AI Lab · Bocconi University

Temporal Video GroundingVisual Spatial ReasoningSpatiotemporal ReasoningEgocentric VQALarge Vision-Language Models3D Visual Question Answering
AskPDF
Sep 27, 2026

SpatialSpeak: QA-Native Reconstruction with Local and Global Context for Spatial Chain-of-Thought Reasoning

Vision-language models (VLMs) can benefit from geometric priors for multi-view spatial reasoning, yet answer-only training does not directly supervise the intermediate geometric estimates and their use in deriving quantitative spatial answers. We hypothesize that spatial chain-of-thought (CoT) supervision becomes more effective when the VLM first jointly learns complementary local geometry and global scene context through multi-view reconstruction. We introduce SpatialSpeak, a two-stage framework that connects QA-native reconstruction pretraining with spatial CoT learning. In Stage I, QA-Native Reconstruction Pretraining (QA-RP) combines marked-point 3D queries for fine-grained local geometry with object-center queries for global scene context across views. Both tasks are formulated as text-based question answering, allowing geometric estimation and subsequent reasoning to share the same autoregressive output interface. In Stage II, spatial CoT with Visual Compensation (CoT-VC) trains the model to express question-relevant geometric estimates and use them to derive answers, with reliability assessment and visual compensation supporting answer refinement when needed. On ReVSI, QA-RP increases the gain from CoT-VC from 2.6 to 6.9 points, and ablations show that both local and global reconstruction supervision are beneficial. SpatialSpeak achieves state-of-the-art results on ReVSI, VSI-Bench, and SPAR-Bench, with a ReVSI score of 62.8 that exceeds the strongest compared baseline by 8.7 points.

Yang Cao, Jiaxin Zhang, Dave Zhenyu Chen +4

Hong Kong University of Science and Technology · Harbin Institute of Technology · Huawei Noah’s Ark Lab

Visual Spatial ReasoningMulti-View 3D ReconstructionVLM Reasoning3D Visual Question Answering3D Spatial ReasoningSpatial Reasoning in Language Models+2
AskPDF
Sep 27, 2026

SceneScaffold: Active Scene-State Construction for Unified 3D Scene Understanding

Recent 3D large multimodal models (3D-LMMs) rely on a visual bottleneck to compress complex 3D scene evidence into a limited number of visual tokens compatible with large language models (LLMs). Current visual bottlenecks, however, often passively compress heterogeneous 3D evidence into a homogeneous object-centric token sequence, leaving the spatial organization of the scene under-represented. This under-representation forces the LLM to recover spatial relations from a flattened token sequence, leading to unstable reasoning in relation-intensive and spatially ambiguous scenes. To address this issue, we propose SceneScaffold, an active scene-state construction framework for unified 3D scene understanding. SceneScaffold reformulates the visual bottleneck from a passive feature compressor into an active scene organizer, constructing a role-aware spatial scaffold before language reasoning. Specifically, SceneScaffold organizes superpoint-level visual evidence into scene-state components with distinct structural roles: entity states preserve core object semantics, scene-frame states maintain spatial references via boundary and region anchors, relation states encode object-environment interaction cues, and a global summary provides compact context. Through this role-aware construction, SceneScaffold provides the LLM with a spatially organized scene representation before language reasoning. Experiments on unified 3D scene understanding tasks, including 3D visual grounding, question answering, and dense captioning, demonstrate the effectiveness of SceneScaffold, while diagnostic results further show its applicability to relation-intensive and spatially ambiguous cases. Code is available at https://github.com/lixiangqi707/SceneScaffold.

Xiangqi Li, Libo Huang, Jiarui Zhao +4

State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences

3D Scene Representation3D Visual Question Answering3D Scene Understanding3D VLMs3D Visual Grounding
AskPDF
Sep 26, 2026

CityToolVQA: Tool-Augmented Visual Question Answering for 3D Spatial Cognition in Urban Low-Altitude Environments

CityToolVQA addresses the weak performance of Vision-Language Models (VLMs) on quantitative tasks in urban low-altitude visual question answering. We divide the seven tasks into qualitative and quantitative groups: qualitative questions are answered directly by the VLM, whereas quantitative questions are handled by an external visual-geometric toolchain that performs object grounding, segmentation, depth back-projection, and spatial computation. The toolchain can be attached to different VLMs in a zero-shot manner; a Depth-Assisted Prompt Inference (DAPI) fallback is triggered when the main-chain detection is invalid or unreliable, and CityToolVQA-SFT adapts the 8B backbone to tool-conditioned inputs. On the 73,324-question Open3D-VQA-v2 test set, CityToolVQA-SFT (Qwen3-VL-8B) reaches 67.6% overall accuracy, and attaching the toolchain to ten open-source VLMs improves quantitative-task accuracy by 12.7-36.9 percentage points. These results indicate that externalizing explicit 3D geometric computation effectively complements the limited ability of RGB-only VLMs to estimate metric distances and object sizes.

Boao Yu, Yingzhen Nie, Yue Hu +2

College of Systems Engineering, National University of Defense Technology · National Key Laboratory of Digital Intelligent Modeling and Simulation

3D Visual Question AnsweringTool Use in VLMsVisual Spatial Reasoning
AskPDF
Sep 14, 2026

SparseTalk - Sparsifying 3D Gaussian Language Fields for Efficient 3D Visual Question Answering

3D Gaussian language fields provide an explicit, spatially grounded representation for 3D visual question answering (VQA), but their dense semantic features can require tens of thousands of embeddings per scene, resulting in substantial storage, memory, and inference costs. We investigate how much of this representation is actually necessary for downstream reasoning. Starting from a full embedding representation, we systematically sparsify its semantic embeddings, including the previously underexplored regime below a single image-equivalent block down to 8 visual tokens. We compare random, geometric, semantic, and joint spatial-semantic selection strategies and introduce an object-based sparsification method that distributes the token budget across detected object instances while retaining background context. Experiments on ScanQA and MV-ScanQA reveal substantial redundancy in dense Gaussian language fields. Strong VQA performance is retained with only a few hundred semantic embeddings, corresponding to less than 1% of the original representation. Object-based selection performs well relative to others, with only modest observed changes down to 256 tokens. At this budget, SparseTalk retains 0.80% of SplatTalk's 32,076-token inference input and 0.332% of the mean 77,207-Gaussian dense field, increasing inference throughput while reducing decoded-feature memory 125-fold.

Davit Soselia, Joseph JaJa, Amitabh Varshney

University of Maryland, College Park, MD, USA

3DGS CompressionLanguage-Embedded 3DGS3D Visual Question AnsweringVisual Token Compression
AskPDF
Sep 3, 2026

GraFT: A Training-Free Framework for Spatial Reasoning in Multimodal Large Language Models via 3D Scene Graphs

3D spatial reasoning underpins understanding and acting in the physical world, yet it remains unreliable in current multimodal large language models (MLLMs). These models falter at precise geometric measurement, at transforming between egocentric and allocentric viewpoints, and at grounding fine-grained appearance. The most common remedies fine-tune the model on large-scale curated spatial-reasoning datasets or attach dedicated encoders for 3D geometry, which typically couples the solution to costly supervision and a specific backbone. We instead introduce GraFT, a training-free framework that supplies the missing 3D structure through a compact, easily maintained 3D scene graph (3DSG). GraFT supplies the graph's 3D structure to the frozen model in three forms: as values computed by symbolic tools, as a bird's-eye-view (BEV) the model reads as an image, and as egocentric frames the geometry selects. On ScanQA, GraFT improves every metric over the same-backbone baseline, raising CIDEr by 27%. On VSI-Bench, GraFT improves frozen MLLMs by up to 65%, surpassing every proprietary and general-purpose open-source baseline, and several prominent fine-tuned spatial models.

Junqing Du, Fernando Ropero, Erkin Turkoz +2

Riemann Lab, Huawei Technologies

3D Spatial ReasoningMultimodal Large Language Models3D Visual Question Answering3D Scene Understanding
AskPDF
Sep 3, 2026

MetaStructAtlas: A Grounded 3D Vision-Language Dataset and Benchmark for Functional and Structural Reasoning in Whole-Body PET/CT

The joint interpretation of metabolic function and anatomical structure is essential for clinical diagnosis in whole-body PET/CT. Although recent advances in 3D medical vision-language models have demonstrated remarkable progress, current efforts are limited to regional CT imaging, leaving a critical void in comprehensive whole-body PET/CT analysis. In this work, we introduce MetaStructAtlas, a large-scale dataset for grounded whole-body PET/CT interpretation that synthesizes multimodal imaging with integrated anatomical, metabolic, and semantic annotations. MetaStructAtlas provides 490 co-registered 3D PET and CT volumes with 50,470 organ-level segmentation masks and grounded radiology reports. To facilitate interactive reasoning, we further developed MetaStructVQA, a standardized 3D grounded visual question-answering benchmark containing 100,565 QA pairs. This framework explicitly links diagnostic queries to visual evidence across modalities, encompassing anatomical, morphological, and metabolic characteristics. Finally, we evaluate state-of-the-art 3D medical VLMs on MetaStructVQA, establishing a robust foundation for multimodal representation learning and integrated whole-body reasoning in nuclear medicine.

Chenguang Zheng, Le Xue, Yichi Zhang +8

Huashan Hospital & Human Phenome Institute, Fudan University, Shanghai, China · Shanghai Academy of Artificial Intelligence for Science, Shanghai, China · Artificial Intelligence Innovation and Incubation Institute, Fudan University, Shanghai, China +1

PET/CT ImagingMedical VLMsMedical Image Grounding3D Visual Question AnsweringMedical Image Benchmarks
AskPDF
Aug 28, 2026

Inter-3D VQA: A Roadside Multimodal Benchmark for 3D Spatiotemporally Grounded Visual Question Answering

Recent advances in visual question answering (VQA) and multimodal large language models (MLLMs) have enabled natural-language reasoning over traffic scenes. However, existing benchmarks are largely built from ego-vehicle views or 2D roadside videos, limiting their ability to evaluate 3D-grounded reasoning over real-world distances, trajectories, infrastructure topology, and safety-critical interactions. We introduce Inter-3D VQA, a large-scale roadside multimodal benchmark for 3D spatiotemporally grounded VQA at intersections. Built from synchronized point clouds and multi-view images, Inter-3D VQA contains 407K QA pairs covering lane-level positions, object relationships, motion patterns, and near-miss-oriented interaction reasoning. We further propose Inter-Geo, an MLLM baseline that integrates object- and scene-level aligned LiDAR representations, and Inter-Metrics, a unified evaluation framework for textual consistency, numerical accuracy, and semantic correctness. Experiments show that Inter-Geo outperforms image-based VLMs, especially on grounded spatial and temporal reasoning tasks. Our benchmark and codes are available at https://github.com/ASU-Suo-Lab/Inter-3D-VQA .

Shaozu Ding, Linan Song, Dajiang Suo

The Polytechnic School, Arizona State University

3D Visual Question AnsweringSpatial Reasoning BenchmarksAutonomous Driving BenchmarksVLMs for Autonomous Driving3D VLMs
AskPDF
Aug 18, 2026

Memory Tree Guided Key Frame Querying for Efficient 3D Question Answering

Answering questions accurately and efficiently in embodied scenarios presents significant challenges due to limited computational and memory resources for Vision Language Model (VLM) inference. Existing methods adopt visual search key frame retrieval method to select critical question-related key frames for VLM input. However, visual search methods are inefficient because they require visual search among thousands of video frames for each individual user query. In this work, we propose a memory tree guided key frame selection paradigm for efficient 3D question answering in embodied scenarios. Our method leverages a compact and reusable 3D scene representation, termed MemTree3D, which supports real-time online construction leveraging camera 6-DoF poses. MemTree3D captures multi-level 3D scene information, enabling a Large Language Model to efficiently query and retrieve question-relevant key frames through our scoring-based frame selection without reprocessing the entire video stream. On OpenEQA, our method improves the LLM-Match of GPT-4o by 17.4%, LLaVA-OneVision-7B by 5.8%, outperforms existing visual search methods. Our code is available at https://github.com/hsiangwei0903/MemTree3D

Hsiang-Wei Huang, Fu-Chen Chen, Li-Wu Tsao +7

University of Washington, United States · Amazon, United States · The University of Texas at Austin, United States

Embodied QA3D Visual Question AnsweringQuery-Aware Video Frame SelectionMemory-Augmented Video UnderstandingOpen-Domain QA
AskPDF
Aug 4, 2026

Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding

Large Multimodal Models (LMMs) have achieved remarkable success on images and short videos, yet scaling them to long videos remains challenging due to frame-centric tokenization and limited context windows. 3D geometry provides a natural compression mechanism for visual streams: depth and camera pose enable observations from multiple views and time steps to be fused into a persistent, world-aligned representation. While recent 3D LMMs leverage geometry-aware representations to improve spatial reasoning, they continue to lag behind specialist 3D perception systems on grounding and segmentation tasks. We argue that a key limitation is geometry-aware decoding: existing methods communicate 3D predictions through language tokens, proposal selection, or lightweight grounding queries, creating a bottleneck between language reasoning and dense geometric prediction. Building on these insights, we introduce Qwen-3D, a geometry-aware LMM that compresses visual information within the Qwen backbone using multi-view geometric cues, enabling efficient long-horizon visual reasoning over static scenes. Qwen-3D augments visual tokens with 3D Rotary Positional Embeddings, allowing attention to operate directly in 3D scene space rather than across independent image frames and thereby facilitating scalable cross-view and temporal reasoning. To bridge language and geometry, Qwen-3D incorporates a query-based segmentation decoder that grounds language directly in the underlying 3D scene representation, unifying referential grounding, instance segmentation, and visual question answering across both images and videos. Across a diverse set of benchmarks, Qwen-3D surpasses existing 3D LMMs and outperforms several large proprietary 2D models. Notably, Qwen-3D achieves these improvements while maintaining strong performance on standard 2D vision-language benchmarks by jointly training on 2D and 3D data.

Lucy Lin, Ayush Jain, Yifan Liu +1

Carnegie Mellon University

3D Foundation Models3D Visual Question Answering3D Instance Segmentation3D Scene Understanding3D VLMs3D Visual Grounding
AskPDF
Aug 2, 2026

3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering

Recent 3D vision-language models (3D VLMs) construct geometry aware tokens by projecting 2D visual features into world coordinates, enabling spatial reasoning for tasks such as 3D question answering. However, this design generates thousands of tokens per scene, resulting in substantial computational and memory overhead. While token compression has been extensively studied in 2D VLMs, existing approaches rely on semantic relevance or attention-based selection that overlook the structured spatial nature of 3D tokens. Moreover, redundancy in 3D representations cannot be resolved by spatial proximity alone, as object-level token imbalance persists even after spatial aggregation. To address this, we propose 3DZip, a three-stage token compression framework that first applies coarse voxelization to remove point-level redundancy, then selects anchor tokens based on feature-space diversity via a Determinantal Point Process, and finally merges remaining tokens under spatial constraints to preserve geometric coherence. Experiments on three 3D question answering benchmarks demonstrate that 3DZip consistently outperforms existing compression methods, retaining 94.7% of the original performance with only 128 tokens, achieving a 1.92×1.92\times faster inference speed.

Changwoo Baek, Kyeongbo Kong

Department of Electrical and Electronics Engineering, Pusan National University, Busan, Republic of Korea

Multimodal Token Compression3D Visual Question Answering3D VLMs
AskPDF
Jul 30, 2026

ViewMind3D: Modular View-Aware Inference for Training-Free 3D-QA

Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled new possibilities for 3D question answering (3D-QA), a key capability for embodied AI and robotic perception. However, most existing methods rely on 3D-specific training or fine-tuning with costly annotations, limiting their scalability and real-world applicability. We present ViewMind3D, a fully training-free and modular framework for 3D spatial reasoning over multi-view observations of a scene without requiring complete 3D reconstruction. The framework decomposes the 3D-QA task into four interpretable components: (1) question-driven multi-view selection, (2) guided visual grounding with language-conditioned object cues, (3) spatial context encoding via a bird's-eye-view (BEV) viewpoint indicator, and (4) structured answer generation through role-based reasoning. This design enables structured, robust, and interpretable reasoning without requiring model tuning. Experimental results on ScanQA and SQA3D show that ViewMind3D achieves competitive performance compared to prior training-free and fine-tuned 3D-LLMs. In particular, our method improves performance on spatially grounded question types, such as ``What'' questions in SQA3D, while maintaining strong overall accuracy (50.8%) and achieving 73.4 CIDEr on ScanQA. These results demonstrate that effective 3D reasoning can be achieved through modular orchestration of general-purpose LLMs and VLMs for robotic perception in real-world environments.

Ping-Kun Chiang, Kun-Ru Wu, Po-han Li +3

3D Spatial ReasoningVLM Reasoning3D Visual Question Answering3D Visual Grounding
AskPDF
Jul 5, 2026

Seeing Once is Enough? Online Geometry-Aware Token Pruning for 3D Question Answering

Recent Multi-modal Large Language Models (MLLMs) have demonstrated remarkable performance on 2D question answering tasks. However, extending these models to the 3D question answering remains challenging, as they typically require multiple views of the scene, which incurs substantial computational cost at inference. To mitigate this issue, existing solutions rely on strategic frame selection or token-merging algorithms that require preprocessing in advance all frames of the scene, i.e., an offline fashion. In contrast, we propose the first online token-pruning method that can be integrated seamlessly with current MLLM models for 3D question answering tasks, without additional training and with lower memory usage.Our key insight is to project each input frame into a shared voxel space using depth information and camera pose, identifying spatially-overlapped regions across frames and selectively pruning redundant image tokens before they enter the language model. Our method enables efficient online processing while reducing up to 50% of token usage. We apply this approach to Qwen2.5-VL-7B and Qwen3-VL-8B, demonstrating improved performance on the ScanQA, SQA3D, and OpenEQA-HM3D benchmarks.

Ruei-Chi Lai, Bolivar Solarte, Chin-Hsuan Wu +2

National Tsing Hua University · Industrial Technology Research Institute ITRI · University of Toronto +1

Efficient VLM InferenceMultimodal QA3D Visual Question AnsweringVisual Token Pruning3D Scene Understanding
AskPDF
Jun 22, 2026

Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views

Multi-view 3D Visual Question Answering (MV3D-VQA) requires integrating partial observations into a coherent 3D scene representation and selecting informative viewpoints for multi-step spatial reasoning. However, current multimodal LLMs are typically trained with sparse, answer-level supervision, which often yields inconsistent cross-view reasoning and brittle view selection. We present DR-MV3D (Dense Reward for MV3D-VQA), a map-grounded learning framework that provides dense, verifiable rewards to supervise the reasoning process. Our approach decomposes MV3D-VQA into (i) allocentric global map construction, (ii) question-conditioned view-trajectory planning, and (iii) egocentric grounding for answer prediction. To make intermediate steps learnable without manual annotations, we introduce two rewards: a global consistency reward that aligns the predicted map with geometry-consistent pseudo targets from frozen 3D vision foundation models (e.g., VGGT + SAM3), and a local trajectory reward that supervises ordered viewpoint selection. We optimize the full pipeline with trajectory-level policy optimization (GRPO). Experiments on MindCube, VSI-Bench, and BLINK (MV) show that DR-MV3D consistently improves over strong multi-image baselines, supporting the effectiveness of process-level dense supervision for multi-view 3D reasoning.

Jiho Choi, Seonho Lee, Seojeong Park +1

Graduate School of Artificial Intelligence, KAIST, Republic of Korea · KRAFTON, Republic of Korea

Visual Question AnsweringActive Perception3D Spatial ReasoningMultimodal Reward ModelingVisually Grounded ReasoningActive View Selection+2
AskPDF
Jun 18, 2026

Occ-VLM: Occupancy Grounded Vision Language Model for Indoor Scene Understanding

Recently, vision-language models (VLMs) have made significant progress in 3D scene understanding, driving advances in applications such as embodied intelligence and robotic vision. However, existing approaches typically either rely directly on explicit 3D inputs (e.g., point clouds or RGB-D sequences), or introduce an additional 3D geometry encoder to derive 3D-aware visual tokens from 2D images. Such designs structurally decouple 3D geometric perception from the rich 2D semantics learned via vision-language pre-training, hindering the development of a unified 3D vision-language representation. In this work, we propose Occ-VLM, a novel framework for 3D scene understanding that operates purely on posed RGB images and employs a single 2D vision encoder. Specifically, Occ-VLM reconstructs 3D scene occupancy as an auxiliary geometric prior, which is utilized to spatially associate foreground 2D tokens with 3D space. These tokens are then decoded by a Large Language Model (LLM) for unified scene understanding. Extensive experiments demonstrate that Occ-VLM achieves both accurate geometric perception and robust vision-language reasoning: it attains state-of-the-art performance on multi-view occupancy prediction, while performing on par with 3D-input VLMs on 3D Visual Question Answering (VQA) and 3D dense captioning benchmarks.

Jianing Li, Zhou Fang, Yijiang Liu +1

School of Electronic Science and Engineering, Nanjing University

3D Occupancy Prediction3D Visual Question Answering3D Scene Understanding3D VLMs
AskPDF
Jun 10, 2026

UniReason-Med: A Shared Grounded Reasoning Interface for 2D-to-3D Transfer in Medical VQA

We study whether grounded reasoning supervision from abundant 2D medical images can improve 3D medical VQA when both input types are aligned through a common reasoning interface. We introduce UniReason-Med, a single-checkpoint framework that processes either a 2D image or a slice-serialized 3D volume at inference time, generating interleaved textual reasoning and localized visual evidence through shared box syntax, region-token injection, and a common grounded reasoning policy. To train this interface, we construct UniMed-CoT, a 220K instruction-tuning dataset with interleaved textual reasoning and grounded visual evidence, including 170K 2D and 50K 3D samples. Through supervised fine-tuning followed by outcome-level reinforcement learning, UniReason-Med learns to generate grounded reasoning traces without IoU/Dice-based localization rewards during RL. Data-mixture and component ablations show that joint 2D+3D grounded supervision substantially improves 3D reasoning over 3D-only training, while grounding and region-token injection consistently benefit both 2D and 3D tasks. These results suggest that a shared grounded reasoning interface can transfer reasoning structure from 2D images to slice-serialized volumetric medical understanding. The code and data are publicly available at https://github.com/IQuestLab/unireason-med.

Mengzhuo Chen, Yan Shu, Chi Liu +4

IQuest Research

Medical Visual Question AnsweringVLM ReasoningTransfer LearningVisually Grounded ReasoningMedical Image Grounding3D Visual Question Answering
AskPDF
Jun 5, 2026

Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry Priors

Despite advances in 3D scene understanding, existing 3D Large Multimodal Models operate in offline settings, requiring complete scene observations or predefined video clips. In this paper, we present an online 3D vision-language model that enables real-time spatial understanding from streaming video. Our approach adopts an autoregressive streaming control modeling based on the LLM's next-token prediction objective to learn when to respond, and employs a lightweight Visual-Spatial Feature Integration (VSFI) module to incrementally inject temporally aligned geometry priors into the visual stream. To alleviate long-context decoding overhead, we propose a plug-and-play Geometry-Adaptive Voxel Compression (GAVC) module for efficient visual token compression. To address the scarcity of streaming 3D-language data, we further develop a scalable data generation pipeline that curates over 1M online spatio-temporal 3D QA pairs and establishes a comprehensive benchmark spanning 29 tasks. Extensive experiments show that our approach significantly outperforms both proprietary and open-source models across online and offline 3D spatial understanding, reasoning, and grounding tasks. The project page is available at https://stream3d-vlm.github.io/

Hanxun Yu, Xuan Qu, Lei Ke +4

1Zhejiang University · 2Tencent Hunyuan · 3HKUST +1

3D Spatial Reasoning3D Visual Question AnsweringVisual Token Compression3D VLMs3D Visual Grounding
AskPDF
Jun 4, 2026

PAR3D: A Unified 3D-MLLM with Part-Aware Representation for Scene Understanding

Recent advances in 3D multimodal large language models (3D-MLLMs) have enabled unified solutions for 3D scene understanding tasks, including visual question answering, captioning, and referring segmentation. However, existing 3D-MLLMs remain largely object-centric, limiting their ability to model fine-grained part structures that are essential for embodied interaction with 3D environments. In this work, we present PAR3D, a unified part-aware 3D-MLLM framework that enables models to understand, reason about, and ground both objects and their parts in 3D scenes. To enable training and evaluation of part-aware 3D scene understanding, we introduce ScenePart, a synthetic 3D scene dataset with part-level annotations and language instructions. We further develop Part-Aware 3D Representation Learning to enrich 3D visual representations with fine-grained part-level semantics, and propose Hierarchical Segmentation Query Generation to ground part targets via hierarchical object-part queries. Extensive experiments show that our method substantially improves part-level question answering and referring segmentation, while also achieving strong performance across object-level vision-language tasks.

Shaohui Dai, Yansong Qu, You Shen +2

Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University

3D Part Segmentation3D Representation Learning3D Visual Question Answering3D Scene Understanding3D VLMs3D Visual Grounding
AskPDF
Jun 2, 2026

Zero-Shot 3D Question Answering via Hierarchical View-to-Token Transportation

Recently, zero-shot 3D scene understanding via 2D Vision-Language Models (VLMs) has gained increasing research interest due to their promising spatial reasoning capabilities. Typically, multiple 2D views are sampled from a 3D point cloud and fed into pre-trained VLMs to answer a given question. This paradigm highlights the critical role of input context quality and raises the challenge of retaining as many task-relevant 3D details as possible under a limited input budget. We propose KeyVT, a hierarchical approach for input context collection at both the view and token levels. Specifically, we combine pixel features with camera parameters and assess view importance based on both semantic content and geometric position, resulting in spatially consistent and task-relevant views. Furthermore, we address redundancy among patches across selected views by identifying representative tokens under the optimal transport (OT) framework, where view tokens and key tokens are formulated as two discrete distributions in the embedding space. These key tokens are expected to cover all view features by minimizing the OT distance. We evaluate our framework on three widely used benchmarks, demonstrating significant improvements over existing tuning-free methods and performance comparable to training-based approaches.

Dongsheng Wang, Dawei Su, Hui Huang

College of Computer Science and Software Engineering, Shenzhen University, China.

3D Visual Question AnsweringVisual Token Compression3D Scene Understanding
AskPDF