3D ViTs

ViT: Vision Transformer

Follow this topic Ask about this topic

3D Vision Transformers apply attention to volumetric images, point clouds, meshes, and multi-view images to learn spatial structure for tasks such as medical segmentation, object detection, and scene reconstruction. Common approaches include voxel or point-token encoders, query-based decoders, camera- or geometry-aware positional encodings, and fusion across views or modalities. They are evaluated on benchmarks including ScanNet, nuScenes, BraTS, and ShapeNet, with newer work also adapting pretrained geometry models to streaming video and long sequences. A central tension is how to preserve fine geometric detail and cross-view consistency while reducing the memory and computation required by attention, especially when transferring across sensors and domains.

Latest papers

145 papers14 papers in the last four weeks, down 7% on the four weeks before. 0.1% of all new papers.

Apr 16, 2026

R3D: Revisiting 3D Policy Learning

3D policy learning promises superior generalization and cross-embodiment transfer, but progress has been hindered by training instabilities and severe overfitting, precluding the adoption of powerful 3D perception models. In this work, we systematically diagnose these failures, identifying the omission of 3D data augmentation and the adverse effects of Batch Normalization as primary causes. We propose a new architecture coupling a scalable transformer-based 3D encoder with a diffusion decoder, engineered specifically for stability at scale and designed to leverage large-scale pre-training. Our approach significantly outperforms state-of-the-art 3D baselines on challenging manipulation benchmarks, establishing a new and robust foundation for scalable 3D imitation learning. Project Page: https://r3d-policy.github.io/

Zhengdong Hong, Shenrui Wu, Haozhe Cui +8

Zhejiang University · ShanghaiTech University

3D ViTs Visuomotor Policy Learning Diffusion Policy Imitation Learning Robot Imitation Learning

Apr 16, 2026

TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens

In this work, we revisit several key design choices of modern Transformer-based approaches for feed-forward 3D Gaussian Splatting (3DGS) prediction. We argue that the common practice of regressing Gaussian means as depths along camera rays is suboptimal, and instead propose to directly regress 3D mean coordinates using only a self-supervised rendering loss. This formulation allows us to move from the standard encoder-only design to an encoder-decoder architecture with learnable Gaussian tokens, thereby unbinding the number of predicted primitives from input image resolution and number of views. Our resulting method, TokenGS, demonstrates improved robustness to pose noise and multiview inconsistencies, while naturally supporting efficient test-time optimization in token space without degrading learned priors. TokenGS achieves state-of-the-art feed-forward reconstruction performance on both static and dynamic scenes, producing more regularized geometry and more balanced 3DGS distribution, while seamlessly recovering emergent scene attributes such as static-dynamic decomposition and scene flow.

Jiawei Ren, Michal Jan Tyszkiewicz, Jiahui Huang +1

NVIDIA

3D Gaussian Splatting 3D ViTs Dynamic Scene Reconstruction Feed-Forward 3D Reconstruction

Apr 16, 2026

StreamCacheVGGT: Streaming Visual Geometry Transformers with Robust Scoring and Hybrid Cache Compression

Reconstructing dense 3D geometry from continuous video streams requires stable inference under a constant memory budget. Existing

O(1)

frameworks primarily rely on a ``pure eviction'' paradigm, which suffers from significant information destruction due to binary token deletion and evaluation noise from localized, single-layer scoring. To address these bottlenecks, we propose StreamCacheVGGT, a training-free framework that reimagines cache management through two synergistic modules: Cross-Layer Consistency-Enhanced Scoring (CLCES) and Hybrid Cache Compression (HCC). CLCES mitigates activation noise by tracking token importance trajectories across the Transformer hierarchy, employing order-statistical analysis to identify sustained geometric salience. Leveraging these robust scores, HCC transcends simple eviction by introducing a three-tier triage strategy that merges moderately important tokens into retained anchors via nearest-neighbor assignment on the key-vector manifold. This approach preserves essential geometric context that would otherwise be lost. Extensive evaluations on five benchmarks (7-Scenes, NRGBD, ETH3D, Bonn, and KITTI) demonstrate that StreamCacheVGGT sets a new state-of-the-art, delivering superior reconstruction accuracy and long-term stability while strictly adhering to constant-cost constraints.

Xuanyi Liu, Chunan Yu, Deyi Ji +6

KOKONI 3D, Moxin Technology · Nanjing University of Science and Technology · University of Science and Technology of China +4

3D ViTs Streaming 3D Reconstruction KV Caching 3D Reconstruction Efficient ViTs Visual Token Compression+1

Apr 15, 2026

LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction

Streaming 3D reconstruction aims to recover 3D information, such as camera poses and point clouds, from a video stream, which necessitates geometric accuracy, temporal consistency, and computational efficiency. Motivated by the principles of Simultaneous Localization and Mapping (SLAM), we introduce LingBot-Map, a feed-forward 3D foundation model for reconstructing scenes from streaming data, built upon a geometric context transformer (GCT) architecture. A defining aspect of LingBot-Map lies in its carefully designed attention mechanism, which integrates an anchor context, a pose-reference window, and a trajectory memory to address coordinate grounding, dense geometric cues, and long-range drift correction, respectively. This design keeps the streaming state compact while retaining rich geometric context, enabling stable efficient inference at around 20 FPS on 518 x 378 resolution inputs over long sequences exceeding 10,000 frames. Extensive evaluations across a variety of benchmarks demonstrate that our approach achieves superior performance compared to both existing streaming and iterative optimization-based approaches.

Lin-Zhuo Chen, Jian Gao, Shangzhan Zhang +9

3D ViTs Streaming 3D Reconstruction 3D Reconstruction Feed-Forward 3D Reconstruction

Apr 15, 2026

Efficient Multi-View 3D Object Detection by Dynamic Token Selection and Fine-Tuning

Existing multi-view three-dimensional (3D) object detection approaches widely adopt large-scale pre-trained vision transformer (ViT)-based foundation models as backbones, being computationally complex. To address this problem, current state-of-the-art (SOTA) ToC3D for efficient multi-view ViT-based 3D object detection employs ego-motion-based relevant token selection. However, there are two key limitations: (1) The fixed layer-individual token selection ratios limit computational efficiency during both training and inference. (2) Full end-to-end retraining of the ViT backbone is required for the multi-view 3D object detection method. In this work, we propose an image token compensator combined with a token selection for ViT backbones to accelerate multi-view 3D object detection. Unlike ToC3D, our approach enables dynamic layer-wise token selection within the ViT backbone. Furthermore, we introduce a parameter-efficient fine-tuning strategy, which trains only the proposed modules, thereby reducing the number of fine-tuned parameters from more than

300

million (M) to only

1.6

M. Experiments on the large-scale NuScenes dataset across three multi-view 3D object detection approaches demonstrate that our proposed method decreases computational complexity (GFLOPs) by

48\%

...

55\%

, inference latency (on an NVIDIA-GV100 GPU) by

9\%

...

25\%

, while still improving mean average precision by

1.0\%

...

2.8\%

absolute and NuScenes detection score by

0.4\%

...

1.2\%

absolute compared to so-far SOTA ToC3D.

Danish Nazir, Antoine Hanna-Asaad, Lucas Görnhardt +3

Group Innovation, Volkswagen AG, 38440, Wolfsburg, Germany · Institute for Communications Technology, Technische Universität Braunschweig, 38106 Braunschweig, Germany

Multi-View 3D Object Detection 3D ViTs Efficient ViTs Token Pruning Parameter-Efficient Fine-Tuning

Apr 10, 2026

Robust 4D Visual Geometry Transformer with Uncertainty-Aware Priors

Reconstructing dynamic 4D scenes is an important yet challenging task. While 3D foundation models like VGGT excel in static settings, they often struggle with dynamic sequences where motion causes significant geometric ambiguity. To address this, we present a framework designed to disentangle dynamic and static components by modeling uncertainty across different stages of the reconstruction process. Our approach introduces three synergistic mechanisms: (1) Entropy-Guided Subspace Projection, which leverages information-theoretic weighting to adaptively aggregate multi-head attention distributions, effectively isolating dynamic motion cues from semantic noise; (2) Local-Consistency Driven Geometry Purification, which enforces spatial continuity via radius-based neighborhood constraints to eliminate structural outliers; and (3) Uncertainty-Aware Cross-View Consistency, which formulates multi-view projection refinement as a heteroscedastic maximum likelihood estimation problem, utilizing depth confidence as a probabilistic weight. Experiments on dynamic benchmarks show that our approach outperforms current state-of-the-art methods, reducing Mean Accuracy error by 13.43% and improving segmentation F-measure by 10.49%. Our framework maintains the efficiency of feed-forward inference and requires no task-specific fine-tuning or per-scene optimization.

Ying Zang, Yidong Han, Chaotao Ding +8

Huzhou University · KOKONI 3D, Moxin Technology · Univeristy of Science and Technology of China +3

UQ for 3D Reconstruction Dynamic Scene Reconstruction 4D Reconstruction 3D Reconstruction Multi-View 3D Reconstruction 3D ViTs+1

Apr 8, 2026

Insights from Visual Cognition: Understanding Human Action Dynamics with Overall Glance and Refined Gaze Transformer

Recently, Transformer has made significant progress in various vision tasks. To balance computation and efficiency in video tasks, recent works heavily rely on factorized or window-based self-attention. However, these approaches split spatiotemporal correlations between regions of interest in videos, limiting the models' ability to capture motion and long-range dependencies. In this paper, we argue that, similar to the human visual system, the importance of temporal and spatial information varies across different time scales, and attention is allocated sparsely over time through glance and gaze behavior. Is equal consideration of time and space crucial for success in video tasks? Motivated by this understanding, we propose a dual-path network called the Overall Glance and Refined Gaze (OG-ReG) Transformer. The Glance path extracts coarse-grained overall spatiotemporal information, while the Gaze path supplements the Glance path by providing local details. Our model achieves state-of-the-art results on the Kinetics-400, Something-Something v2, and Diving-48, demonstrating its competitive performance. The code will be available at https://github.com/linuxsino/OG-ReG.

Bohao Xing, Deng Li, Rong Gao +2

Department of Computational Engineering, Lappeenranta-Lahti University of Technology LUT, Finland · Faculty of Information Technology, Brno University of Technology, Czech Republic

Video Action Recognition Spatiotemporal Transformers 3D ViTs Temporal Attention

Apr 8, 2026

GPAFormer: Graph-guided Patch Aggregation Transformer for Efficient 3D Medical Image Segmentation

Deep learning has been widely applied to 3D medical image segmentation tasks. However, due to the diversity of imaging modalities, the high-dimensional nature of the data, and the heterogeneity of anatomical structures, achieving both segmentation accuracy and computational efficiency in multi-organ segmentation remains a challenge. This study proposed GPAFormer, a lightweight network architecture specifically designed for 3D medical image segmentation, emphasizing efficiency while keeping high accuracy. GPAFormer incorporated two core modules: the multi-scale attention-guided stacked aggregation (MASA) and the mutual-aware patch graph aggregator (MPGA). MASA utilized three parallel paths with different receptive fields, combined through planar aggregation, to enhance the network's capability in handling structures of varying sizes. MPGA employed a graph-guided approach to dynamically aggregate regions with similar feature distributions based on inter-patch feature similarity and spatial adjacency, thereby improving the discrimination of both internal and boundary structures of organs. Experiments were performed on public whole-body CT and MRI datasets including BTCV, Synapse, ACDC, and BraTS. Compared to the existed 3D segmentation networkd, GPAFormer using only 1.81 M parameters achieved overall highest DSC on BTCV (75.70%), Synapse (81.20%), ACDC (89.32%), and BraTS (82.74%). Using consumer level GPU, the inference time for one validation case of BTCV spent less than one second. The results demonstrated that GPAFormer balanced accuracy and efficiency in multi-organ, multi-modality 3D segmentation tasks across various clinical scenarios especially for resource-constrained and time-sensitive clinical environments.

Chung-Ming Lo, I-Yun Liu, Wei-Yang Lin

Institute of Artificial Intelligence Innovation, Industry Academia Innovation School, National Yang Ming Chiao Tung University · Department of Computer Science and Information Engineering, National Chung Cheng University

Multi-Organ Segmentation Medical Image Segmentation 3D Medical Image Segmentation 3D ViTs

Apr 7, 2026

Geometrical Cross-Attention and Nonvoid Voxelization for Efficient 3D Medical Image Segmentation

Accurate segmentation of 3D medical scans is crucial for clinical diagnostics and treatment planning, yet existing methods often fail to achieve both high accuracy and computational efficiency across diverse anatomies and imaging modalities. To address these challenges, we propose GCNV-Net, a novel 3D medical segmentation framework that integrates a Tri-directional Dynamic Nonvoid Voxel Transformer (3DNVT), a Geometrical Cross-Attention module (GCA), and Nonvoid Voxelization. The 3DNVT dynamically partitions relevant voxels along the three orthogonal anatomical planes, namely the transverse, sagittal, and coronal planes, enabling effective modeling of complex 3D spatial dependencies. The GCA mechanism explicitly incorporates geometric positional information during multi-scale feature fusion, significantly enhancing fine-grained anatomical segmentation accuracy. Meanwhile, Nonvoid Voxelization processes only informative regions, greatly reducing redundant computation without compromising segmentation quality, and achieves a 56.13% reduction in FLOPs and a 68.49% reduction in inference latency compared to conventional voxelization. We evaluate GCNV-Net on multiple widely used benchmarks: BraTS2021, ACDC, MSD Prostate, MSD Pancreas, and AMOS2022. Our method achieves state-of-the-art segmentation performance across all datasets, outperforming the best existing methods by 0.65% on Dice, 0.63% on IoU, 1% on NSD, and relatively 14.5% on HD95. All results demonstrate that GCNV-Net effectively balances accuracy and efficiency, and its robustness across diverse organs, disease conditions, and imaging modalities highlights strong potential for clinical deployment.

Chenxin Yuan, Shoupeng Chen, Haojiang Ye +3

Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, 518100, Guangdong, China · School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, 639798, Singapore · School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Shenzhen, 518172, Guangdong, China +2

3D Medical Image Segmentation 3D ViTs Cross-Attention

Apr 6, 2026

Boxer: Robust Lifting of Open-World 2D Bounding Boxes to 3D

Detecting and localizing objects in space is a fundamental computer vision problem. While much progress has been made to solve 2D object detection, 3D object localization is much less explored and far from solved, especially for open-world categories. To address this research challenge, we propose Boxer, an algorithm to estimate static 3D bounding boxes (3DBBs) from 2D open-vocabulary object detections, posed images and optional depth either represented as a sparse point cloud or dense depth. At its core is BoxerNet, a transformer-based network which lifts 2D bounding box (2DBB) proposals into 3D, followed by multi-view fusion and geometric filtering to produce globally consistent de-duplicated 3DBBs in metric world space. Boxer leverages the power of existing 2DBB detection algorithms (e.g. DETIC, OWLv2, SAM3) to localize objects in 2D. This allows the main BoxerNet model to focus on lifting to 3D rather than detecting, ultimately reducing the demand for costly annotated 3DBB training data. Extending the CuTR formulation, we incorporate an aleatoric uncertainty for robust regression, a median depth patch encoding to support sparse depth inputs, and large-scale training with over 1.2 million unique 3DBBs. BoxerNet outperforms state-of-the-art baselines in open-world 3DBB lifting, including CuTR in egocentric settings without dense depth (0.532 vs. 0.010 mAP) and on CA-1M with dense depth available (0.412 vs. 0.250 mAP).

Daniel DeTone, Tianwei Shen, Fan Zhang +4

Meta Reality Labs Research

3D Object Detection Multi-View 3D Object Detection 3D ViTs 3D Reconstruction

Apr 6, 2026

LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows

We introduce the Large Sparse Reconstruction Model to study how scaling transformer context windows affects feed-forward 3D reconstruction. Although recent object-centric feed-forward methods produce robust, high-quality reconstructions, they still lag behind dense-view optimization in recovering fine-grained texture and appearance. We show that expanding the context window -- by substantially increasing the number of active object and image tokens -- narrows this gap and enables high-fidelity 3D object reconstruction and inverse rendering. To scale effectively, we adapt native sparse attention for 3D reconstruction with three key contributions: (1) an efficient coarse-to-fine pipeline that focuses computation on informative regions by predicting sparse high-resolution residuals; (2) a 3D-aware spatial routing mechanism that establishes accurate 2D-3D correspondences using explicit geometric distances rather than standard attention scores; and (3) a custom block-aware sequence-parallel strategy with an All-gather-KV protocol to balance dynamic, sparse workloads across GPUs. As a result, LSRM handles 20x more object tokens and >2x more image tokens than prior state-of-the-art (SOTA) methods. Extensive evaluations on standard novel-view synthesis benchmarks show substantial gains over the current SOTA, yielding >2.4dB higher PSNR and >40% lower LPIPS. Furthermore, when extending LSRM to inverse rendering, qualitative and quantitative evaluations on widely used benchmarks demonstrate consistent improvements in texture and geometry details, achieving an LPIPS that matches or exceeds that of SOTA dense-view optimization methods. Code and model weights are available on our project page.

Zhengqin Li, Cheng Zhang, Jakob Engel +1

Meta Reality Labs Research

Object-Centric 3D Reconstruction Inverse Rendering 3D ViTs 3D Reconstruction Novel View Synthesis Sparse Attention+1

Apr 4, 2026

Learning 3D Reconstruction with Priors in Test Time

We introduce a test-time framework for multiview Transformers (MVTs) that incorporates priors (e.g., camera poses, intrinsics, and depth) to improve 3D tasks without retraining or modifying pre-trained image-only networks. Rather than feeding priors into the architecture, we cast them as constraints on the predictions and optimize the network at inference time. The optimization loss consists of a self-supervised objective and prior penalty terms. The self-supervised objective captures the compatibility among multi-view predictions and is implemented using photometric or geometric loss between renderings from other views and each view itself. Any available priors are converted into penalty terms on the corresponding output modalities. Across a series of 3D vision benchmarks, including point map estimation and camera pose estimation, our method consistently improves performance over base MVTs by a large margin. On the ETH3D, 7-Scenes, and NRGBD datasets, our method reduces the point-map distance error by more than half compared with the base image-only models. Our method also outperforms retrained prior-aware feed-forward methods, demonstrating the effectiveness of our test-time constrained optimization (TCO) framework for incorporating priors into 3D vision tasks.

Lei Zhou, Haoyu Wu, Akshat Dave +1

Stony Brook University

Multi-View 3D Reconstruction Test-Time Optimization 3D ViTs Camera Pose Estimation

Apr 3, 2026

BEVPredFormer: Spatio-temporal Attention for BEV Instance Prediction in Autonomous Driving

A robust awareness of how dynamic scenes evolve is essential for Autonomous Driving systems, as they must accurately detect, track, and predict the behaviour of surrounding obstacles. Traditional perception pipelines that rely on modular architectures tend to suffer from cumulative errors and latency. Instance Prediction models provide a unified solution, performing Bird's-Eye-View segmentation and motion estimation across current and future frames using information directly obtained from different sensors. However, a key challenge in these models lies in the effective processing of the dense spatial and temporal information inherent in dynamic driving environments. This level of complexity demands architectures capable of capturing fine-grained motion patterns and long-range dependencies without compromising real-time performance. We introduce BEVPredFormer, a novel camera-only architecture for BEV instance prediction that uses attention-based temporal processing to improve temporal and spatial comprehension of the scene and relies on an attention-based 3D projection of the camera information. BEVPredFormer employs a recurrent-free design that incorporates gated transformer layers, divided spatio-temporal attention mechanisms, and multi-scale head tasks. Additionally, we incorporate a difference-guided feature extraction module that enhances temporal representations. Extensive ablation studies validate the effectiveness of each architectural component. When evaluated on the nuScenes dataset, BEVPredFormer was on par or surpassed State-Of-The-Art methods, highlighting its potential for robust and efficient Autonomous Driving perception.

Miguel Antunes-García, Santiago Montiel-Marín, Fabio Sánchez-García +3

RobeSafe Research Group, Department of Electronics, University of Alcalá, Alcalá de Henares, Madrid, Spain.

Autonomous Driving Perception 3D ViTs Temporal Attention

Apr 2, 2026

Semantic Segmentation of Textured Non-manifold 3D Meshes using Transformers

Textured 3D meshes jointly represent geometry, topology, and appearance, yet their irregular structure poses significant challenges for deep-learning-based semantic segmentation. While a few recent methods operate directly on meshes without imposing geometric constraints, they typically overlook the rich textural information also provided by such meshes. We introduce a texture-aware transformer that learns directly from raw pixels associated with each mesh face, coupled with a new hierarchical learning scheme for multi-scale feature aggregation. A texture branch summarizes all face-level pixels into a learnable token, which is fused with geometrical descriptors and processed by a stack of Two-Stage Transformer Blocks (TSTB), which allow for both a local and a global information flow. We evaluate our model on the Semantic Urban Meshes (SUM) benchmark and a newly curated cultural-heritage dataset comprising textured roof tiles with triangle-level annotations for damage types. Our method achieves 81.9% mF1 and 94.3% OA on SUM and 49.7% mF1 and 72.8% OA on the new dataset, substantially outperforming existing approaches.

Mohammadreza Heidarianbaei, Max Mehltretter, Franz Rottensteiner

Institute of Photogrammetry and GeoInformation, Leibniz University Hannover, Germany

3D Semantic Segmentation 3D ViTs

Apr 2, 2026

NEMESIS: Noise-suppressed Efficient MAE with Enhanced Superpatch Integration Strategy

Volumetric CT imaging is essential for clinical diagnosis, yet annotating 3D volumes is expensive and time-consuming, motivating self-supervised learning (SSL) from unlabeled data. However, applying SSL to 3D CT remains challenging due to the high memory cost of full-volume transformers and the anisotropic spatial structure of CT data, which is not well captured by conventional masking strategies. We propose NEMESIS, a masked autoencoder (MAE) framework that operates on local 128x128x128 superpatches, enabling memory-efficient training while preserving anatomical detail. NEMESIS introduces three key components: (i) noise-enhanced reconstruction as a pretext task, (ii) Masked Anatomical Transformer Blocks (MATB) that perform dual-masking through parallel plane-wise and axis-wise token removal, and (iii) NEMESIS Tokens (NT) for cross-scale context aggregation. On the BTCV multi-organ classification benchmark, NEMESIS with a frozen backbone and a linear classifier achieves a mean AUROC of 0.9633, surpassing fully fine-tuned SuPreM (0.9493) and VoCo (0.9387). Under a low-label regime with only 10% of available annotations, it retains an AUROC of 0.9075, demonstrating strong label efficiency. Furthermore, the superpatch-based design reduces computational cost to 31.0 GFLOPs per forward pass, compared to 985.8 GFLOPs for the full-volume baseline, providing a scalable and robust foundation for 3D medical imaging.

Kyeonghun Kim, Hyeonseok Jung, Youngung Han +9

OUTTA · Chung-Ang University · Seoul National University +3

Medical Image Representation Learning Masked Autoencoders Self-Supervised Pre-Training 3D ViTs Medical Image Classification

Apr 1, 2026

DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale

End-to-end autonomous driving has evolved from the conventional paradigm based on sparse perception into vision-language-action (VLA) models, which focus on learning language descriptions as an auxiliary task to facilitate planning. In this paper, we propose an alternative Vision-Geometry-Action (VGA) paradigm that advocates dense 3D geometry as the critical cue for autonomous driving. As vehicles operate in a 3D world, we think dense 3D geometry provides the most comprehensive information for decision-making. However, most existing geometry reconstruction methods (e.g., DVGT) rely on computationally expensive batch processing of multi-frame inputs and cannot be applied to online planning. To address this, we introduce a streaming Driving Visual Geometry Transformer (DVGT-2), which processes inputs in an online manner and jointly outputs dense geometry and trajectory planning for the current frame. We employ temporal causal attention and cache historical features to support on-the-fly inference. To further enhance efficiency, we propose a sliding-window streaming strategy and use historical caches within a certain interval to avoid repetitive computations. Despite the faster speed, DVGT-2 achieves superior geometry reconstruction performance on various datasets. The same trained DVGT-2 can be directly applied to planning across diverse camera configurations without fine-tuning, including closed-loop NAVSIM and open-loop nuScenes benchmarks.

Sicheng Zuo, Zixun Xie, Wenzhao Zheng +6

Tsinghua University · Xiaomi EV · Peking University +1

End-to-End Autonomous Driving Autonomous Driving Planning Streaming 3D Reconstruction 3D ViTs

Mar 28, 2026

HD-VGGT: High-Resolution Visual Geometry Transformer

High-resolution imagery is essential for accurate 3D reconstruction, as many geometric details only emerge at fine spatial scales. Recent feed-forward approaches, such as the Visual Geometry Grounded Transformer (VGGT), have demonstrated the ability to infer scene geometry from large collections of images in a single forward pass. However, scaling these models to high-resolution inputs remains challenging: the number of tokens in transformer architectures grows rapidly with both image resolution and the number of views, leading to prohibitive computational and memory costs. Moreover, we observe that visually ambiguous regions, such as repetitive patterns, weak textures, or specular surfaces, often produce unstable feature tokens that degrade geometric inference, especially at higher resolutions. We introduce HD-VGGT, a dual-branch architecture for efficient and robust high-resolution 3D reconstruction. A low-resolution branch predicts a coarse, globally consistent geometry, while a high-resolution branch refines details via a learned feature upsampling module. To handle unstable tokens, we propose Feature Modulation, which suppresses unreliable features early in the transformer. HD-VGGT leverages high-resolution images and supervision without full-resolution transformer costs, achieving state-of-the-art reconstruction quality.

Tianrun Chen, Yuanqi Hu, Yidong Han +11

KOKONI 3D, Moxin Technology · Zhejiang University · Huzhou University +4

3D Reconstruction 3D ViTs Multi-View 3D Reconstruction Feed-Forward 3D Reconstruction Efficient ViTs

Mar 27, 2026

FAST3DIS: Feed-forward Anchored Scene Transformer for 3D Instance Segmentation

While recent feed-forward 3D reconstruction models provide a strong geometric foundation for scene understanding, extending them to 3D instance segmentation typically relies on a disjointed "lift-and-cluster" paradigm. Grouping dense pixel-wise embeddings via non-differentiable clustering scales poorly with the number of views and disconnects representation learning from the final segmentation objective. In this paper, we present a Feed-forward Anchored Scene Transformer for 3D Instance Segmentation (FAST3DIS), an end-to-end approach that effectively bypasses post-hoc clustering. We introduce a 3D-anchored, query-based Transformer architecture built upon a foundational depth backbone, adapted efficiently to learn instance-specific semantics while retaining its zero-shot geometric priors. We formulate a learned 3D anchor generator coupled with an anchor-sampling cross-attention mechanism for view-consistent 3D instance segmentation. By projecting 3D object queries directly into multi-view feature maps, our method samples context efficiently. Furthermore, we introduce a dual-level regularization strategy, that couples multi-view contrastive learning with a dynamically scheduled spatial overlap penalty to explicitly prevent query collisions and ensure precise instance boundaries. Experiments on complex indoor 3D datasets demonstrate that our approach achieves competitive segmentation accuracy with significantly improved memory scalability and inference speed over state-of-the-art clustering-based methods.

Changyang Li, Xueqing Huang, Shin-Fang Chng +3

Goertek Alpha Labs

Multi-View Contrastive Learning 3D Instance Segmentation 3D ViTs 3D Representation Learning

Mar 26, 2026

Fus3D: Decoding Consolidated 3D Geometry from Feed-forward Geometry Transformer Latents

We propose a feed-forward method for dense Signed Distance Field (SDF) regression from unstructured image collections in less than three seconds, without camera calibration or post-hoc fusion. Our key insight is that the intermediate feature space of pretrained multi-view feed-forward geometry transformers already encodes a powerful joint world representation; yet, existing pipelines discard it, routing features through per-view prediction heads before assembling 3D geometry post-hoc, which discards valuable completeness information and accumulates inaccuracies. We instead perform 3D extraction directly from geometry transformer features via learned volumetric extraction: voxelized canonical embeddings that progressively absorb multi-view geometry information through interleaved cross- and self-attention into a structured volumetric latent grid. A simple convolutional decoder then maps this grid to a dense SDF. We additionally propose a scalable, validity-aware supervision scheme directly using SDFs derived from depth maps or 3D assets, tackling practical issues like non-watertight meshes. Our approach yields complete and well-defined distance values across sparse- and dense-view settings and demonstrates geometrically plausible completions. Code and further material can be found at https://lorafib.github.io/fus3d.

Laura Fink, Linus Franke, George Kopanas +2

Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany · Inria, Université Côte d’Azur, France · Google DeepMind, UK

Feed-Forward 3D Reconstruction Multi-View 3D Reconstruction Sparse-View 3D Reconstruction Signed Distance Functions 3D ViTs

Mar 26, 2026

AdaSFormer: Adaptive Serialized Transformers for Monocular Semantic Scene Completion from Indoor Environments

Indoor monocular semantic scene completion (MSSC) is notably more challenging than its outdoor counterpart due to complex spatial layouts and severe occlusions. While transformers are well suited for modeling global dependencies, their high memory cost and difficulty in reconstructing fine-grained details have limited their use in indoor MSSC. To address these limitations, we introduce AdaSFormer, a serialized transformer framework tailored for indoor MSSC. Our model features three key designs: (1) an Adaptive Serialized Transformer with learnable shifts that dynamically adjust receptive fields; (2) a Center-Relative Positional Encoding that captures spatial information richness; and (3) a Convolution-Modulated Layer Normalization that bridges heterogeneous representations between convolutional and transformer features. Extensive experiments on NYUv2 and Occ-ScanNet demonstrate that AdaSFormer achieves state-of-the-art performance. The code is publicly available at: https://github.com/alanWXZ/AdaSFormer.

Xuzhi Wang, Xinran Wu, Song Wang +2

Tianjin Normal University · Zhejiang University · National University of Singapore

3D Scene Completion 3D ViTs Hybrid CNN-Transformer Architectures

Mar 26, 2026

HeSS: Head Sensitivity Score for Sparsity Redistribution in VGGT

Visual Geometry Grounded Transformer (VGGT) has advanced 3D vision, yet its global attention layers suffer from quadratic computational costs that hinder scalability. Several sparsification-based acceleration techniques have been proposed to alleviate this issue, but they often suffer from substantial accuracy degradation. We hypothesize that the accuracy degradation stems from the heterogeneity in head-wise sparsification sensitivity, as the existing methods apply a uniform sparsity pattern across all heads. Motivated by this hypothesis, we present a two-stage sparsification pipeline that effectively quantifies and exploits headwise sparsification sensitivity. In the first stage, we measure head-wise sparsification sensitivity using a novel metric, the Head Sensitivity Score (HeSS), which approximates the Hessian with respect to two distinct error terms on a small calibration set. In the inference stage, we perform HeSS-Guided Sparsification, leveraging the pre-computed HeSS to reallocate the total attention budget-assigning denser attention to sensitive heads and sparser attention to more robust ones. We demonstrate that HeSS effectively captures head-wise sparsification sensitivity and empirically confirm that attention heads in the global attention layers exhibit heterogeneous sensitivity characteristics. Extensive experiments further show that our method effectively mitigates performance degradation under high sparsity, demonstrating strong robustness across varying sparsification levels. Code is available at https://github.com/libary753/HeSS.

Yongsung Kim, Wooseok Song, Jaihyun Lew +3

IPAI, Seoul National University · ECE, Seoul National University · AIIS, ASRI, INMC, ISRC, Seoul National University

Sparse Attention Efficient ViTs 3D ViTs Attention Head Analysis

Mar 24, 2026

Harnessing Lightweight Transformer with Contextual Synergic Enhancement for Efficient 3D Medical Image Segmentation

Transformers have shown remarkable performance in 3D medical image segmentation, but their high computational requirements and need for large amounts of labeled data limit their applicability. To address these challenges, we consider two crucial aspects: model efficiency and data efficiency. Specifically, we propose Light-UNETR, a lightweight transformer designed to achieve model efficiency. Light-UNETR features a Lightweight Dimension Reductive Attention (LIDR) module, which reduces spatial and channel dimensions while capturing both global and local features via multi-branch attention. Additionally, we introduce a Compact Gated Linear Unit (CGLU) to selectively control channel interaction with minimal parameters. Furthermore, we introduce a Contextual Synergic Enhancement (CSE) learning strategy, which aims to boost the data efficiency of Transformers. It first leverages the extrinsic contextual information to support the learning of unlabeled data with Attention-Guided Replacement, then applies Spatial Masking Consistency that utilizes intrinsic contextual information to enhance the spatial context reasoning for unlabeled data. Extensive experiments on various benchmarks demonstrate the superiority of our approach in both performance and efficiency. For example, with only 10% labeled data on the Left Atrial Segmentation dataset, our method surpasses BCP by 1.43% Jaccard while drastically reducing the FLOPs by 90.8% and parameters by 85.8%. Code is released at https://github.com/CUHK-AIM-Group/Light-UNETR.

Xinyu Liu, Zhen Chen, Wuyang Li +2

Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong SAR · Centre for Artificial Intelligence and Robotics (CAIR), Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences, Hong Kong SAR

3D Medical Image Segmentation 3D ViTs Efficient ViTs Semi-Supervised Medical Image Segmentation

Mar 24, 2026

Object Pose Transformer: Unifying Unseen Object Pose Estimation

Learning model-free object pose estimation for unseen instances remains a fundamental challenge in 3D vision. Existing methods typically fall into two disjoint paradigms: category-level approaches predict absolute poses in a canonical space but rely on predefined taxonomies, while relative pose methods estimate cross-view transformations but cannot recover single-view absolute pose. In this work, we propose Object Pose Transformer (\ours{}), a unified feed-forward framework that bridges these paradigms through task factorization within a single model. \ours{} jointly predicts depth, point maps, camera parameters, and normalized object coordinates (NOCS) from RGB inputs, enabling both category-level absolute SA(3) pose and unseen-object relative SE(3) pose. Our approach leverages contrastive object-centric latent embeddings for canonicalization without requiring semantic labels at inference time, and uses point maps as a camera-space representation to enable multi-view relative geometric reasoning. Through cross-frame feature interaction and shared object embeddings, our model leverages relative geometric consistency across views to improve absolute pose estimation, reducing ambiguity in single-view predictions. Furthermore, \ours{} is camera-agnostic, learning camera intrinsics on-the-fly and supporting optional depth input for metric-scale recovery, while remaining fully functional in RGB-only settings. Extensive experiments on diverse benchmarks (NOCS, HouseCat6D, Omni6DPose, Toyota-Light) demonstrate state-of-the-art performance in both absolute and relative pose estimation tasks within a single unified architecture.

Weihang Li, Lorenzo Garattoni, Fabien Despinoy +2

Technical University of Munich · Munich Center for Machine Learning · Toyota Motor Europe

Object Pose Estimation Relative Pose Estimation 3D ViTs

Mar 23, 2026

SegMaFormer: A Hybrid State-Space and Transformer Model for Efficient Segmentation

The advent of Transformer and Mamba-based architectures has significantly advanced 3D medical image segmentation by enabling global contextual modeling, a capability traditionally limited in Convolutional Neural Networks (CNNs). However, state-of-the-art Transformer models often entail substantial computational complexity and parameter counts, which is particularly prohibitive for volumetric data and further exacerbated by the limited availability of annotated medical imaging datasets. To address these limitations, this work introduces SegMaFormer, a lightweight hybrid architecture that synergizes Mamba and Transformer modules within a hierarchical volumetric encoder for efficient long-range dependency modeling. The model strategically employs Mamba-based layers in early, high-resolution stages to reduce computational overhead while capturing essential spatial context, and reserves self-attention mechanisms for later, lower-resolution stages to refine feature representation. This design is augmented with generalized rotary position embeddings to enhance spatial awareness. Despite its compact structure, SegMaFormer achieves competitive performance on three public benchmarks (Synapse, BraTS, and ACDC), matching the Dice coefficient of significantly larger models. Empirically, our approach reduces parameters by up to 75x and substantially decreases FLOPs compared to current state-of-the-art models, establishing an efficient and high-performing solution for 3D medical image segmentation.

Duy D. Nguyen, Phat T. Tran-Truong

Department of Software Engineering, Faculty of Computer Science and Engineering, Ho Chi Minh City University of Technology (HCMUT), 268 Ly Thuong Kiet Street, Dien Hong Ward, Ho Chi Minh City, Vietnam · Vietnam National University Ho Chi Minh City, Linh Trung Ward, Ho Chi Minh City, Vietnam

Hybrid Transformer-State Space Model Architectures 3D Medical Image Segmentation 3D ViTs Efficient ViTs State Space Models

Mar 20, 2026

SegVGGT: Joint 3D Reconstruction and Instance Segmentation from Multi-View Images

3D instance segmentation methods typically rely on high-quality point clouds or posed RGB-D scans, requiring complex multi-stage processing pipelines, and are highly sensitive to reconstruction noise. While recent feed-forward transformers have revolutionized multi-view 3D reconstruction, they remain decoupled from high-level semantic understanding. In this work, we present SegVGGT, a unified end-to-end framework that simultaneously performs feed-forward 3D reconstruction and instance segmentation directly from multi-view RGB images. By introducing object queries that interact with multi-level geometric features, our method deeply integrates instance identification into the visual geometry grounded transformer. To address the severe attention dispersion problem caused by the massive number of global image tokens, we propose the Frame-level Attention Distribution Alignment (FADA) strategy. FADA explicitly guides object queries to attend to instance-relevant frames during training, providing structured supervision without extra inference overhead. Extensive experiments demonstrate that SegVGGT achieves the state-of-the-art performance on ScanNetv2 and ScanNet200, outperforming both recent joint models and RGB-D-based approaches, while exhibiting strong generalization capabilities on ScanNet++.

Jinyuan Qu, Hongyang Li, Lei Zhang

Tsinghua University · International Digital Economy Academy (IDEA) · South China University of Technology

3D Instance Segmentation Multi-View 3D Reconstruction 3D ViTs Feed-Forward 3D Reconstruction

Mar 19, 2026

SEAR: Simple and Efficient Adaptation of Visual Geometric Transformers for Unpaired RGB+Thermal 3D Reconstruction

Foundational feed-forward visual geometry models enable accurate and efficient camera pose estimation and scene reconstruction by learning strong scene priors from massive RGB datasets. However, their effectiveness drops when applied to mixed sensing modalities, such as RGB-thermal (RGB-T) images. We observe that while a visual geometry grounded transformer pretrained on RGB data generalizes well to thermal-only reconstruction, it struggles to align RGB and thermal modalities when processed jointly. To address this, we propose SEAR, a simple yet efficient fine-tuning strategy that adapts a pretrained geometry transformer to multimodal RGB-T inputs. Despite being trained on a relatively small RGB-T dataset, our approach significantly outperforms state-of-the-art methods for 3D reconstruction and camera pose estimation, achieving significant improvements over all metrics and delivering higher detail and consistency between modalities with negligible overhead in inference time compared to the original pretrained model. Notably, SEAR enables reliable multimodal pose estimation and reconstruction even under challenging conditions, such as low lighting and dense smoke. We validate our architecture through extensive ablation studies and demonstrate how the model aligns both modalities. Additionally, we introduce a new dataset featuring RGB and thermal sequences captured at different times, viewpoints, and illumination conditions, providing a robust benchmark for future work in multimodal 3D scene reconstruction. Code and models are publicly available at https://doi.org/10.5281/ZENODO.21077295.

Vsevolod Skorokhodov, Chenghao Xu, Shuo Sun +2

Schindler EPFL Lab, Lausanne, Switzerland · EPFL, Lausanne, Switzerland · Örebro University, Örebro, Sweden

3D Reconstruction Multi-View 3D Reconstruction Camera Pose Estimation 3D ViTs Multimodal Sensor Fusion

Mar 18, 2026

PanoVGGT: Feed-Forward 3D Reconstruction from Panoramic Imagery

Panoramic imagery offers a full 360° field of view and is increasingly common in consumer devices. However, it introduces non-pinhole distortions that challenge joint pose estimation and 3D reconstruction. Existing feed-forward models, built for perspective cameras, generalize poorly to this setting. We propose PanoVGGT, a permutation-equivariant Transformer framework that jointly predicts camera poses, depth maps, and 3D point clouds from one or multiple panoramas in a single forward pass. The model incorporates spherical-aware positional embeddings and a panorama-specific three-axis SO(3) rotation augmentation, enabling effective geometric reasoning in the spherical domain. To resolve inherent global-frame ambiguity, we further introduce a stochastic anchoring strategy during training. In addition, we contribute PanoCity, a large-scale outdoor panoramic dataset with dense depth and 6-DoF pose annotations. Extensive experiments on PanoCity and standard benchmarks demonstrate that PanoVGGT achieves competitive accuracy, strong robustness, and improved cross-domain generalization. Code and dataset will be released.

Yijing Guo, Mengjun Chao, Luo Wang +5

ShanghaiTech University · Sudo

Panoramic 3D Reconstruction Feed-Forward 3D Reconstruction Camera Pose Estimation 3D ViTs

Mar 18, 2026

STAC: Plug-and-Play Spatio-Temporal Aware Cache Compression for Streaming 3D Reconstruction

Online 3D reconstruction from streaming inputs requires both long-term temporal consistency and efficient memory usage. Although causal variants of VGGT address this challenge through a key-value (KV) cache mechanism, the cache grows linearly with the stream length, creating a major memory bottleneck. Under limited memory budgets, early cache eviction significantly degrades reconstruction quality and temporal consistency. In this work, we observe that attention in causal transformers for 3D reconstruction exhibits intrinsic spatio-temporal sparsity. Based on this insight, we propose STAC, a Spatio-Temporally Aware Cache Compression framework for streaming 3D reconstruction with large causal transformers. STAC consists of three key components: (1) a Working Temporal Token Caching mechanism that preserves long-term informative tokens using decayed cumulative attention scores; (2) a Long-term Spatial Token Caching scheme that compresses spatially redundant tokens into voxel-aligned representations for memory-efficient storage; and (3) a Chunk-based Multi-frame Optimization strategy that jointly processes consecutive frames to improve temporal coherence and GPU efficiency. Extensive experiments show that STAC achieves state-of-the-art reconstruction quality while reducing memory consumption by nearly 10x and accelerating inference by 4x, substantially improving the scalability of real-time 3D reconstruction in streaming settings.

Runze Wang, Yuxuan Song, Youcheng Cai +1

University of Science and Technology of China

Streaming 3D Reconstruction KV-Cache Compression 3D ViTs Visual Token Compression

Mar 18, 2026

Gesture-Aware Pretraining and Token Fusion for 3D Hand Pose Estimation

Estimating 3D hand pose from monocular RGB images is fundamental for applications in AR/VR, human-computer interaction, and sign language understanding. In this work we focus on a scenario where a discrete set of gesture labels is available and show that gesture semantics can serve as a powerful inductive bias for 3D pose estimation. We present a two-stage framework: gesture-aware pretraining that learns an informative embedding space using coarse and fine gesture labels from InterHand2.6M, followed by a per-joint token Transformer guided by gesture embeddings as intermediate representations for final regression of MANO hand parameters. Training is driven by a layered objective over parameters, joints, and structural constraints. Experiments on InterHand2.6M demonstrate that gesture-aware pretraining consistently improves single-hand accuracy over the state-of-the-art EANet baseline, and that the benefit transfers across architectures without any modification.

Rui Hong, Jana Kosecka

George Mason University

3D Hand Pose Estimation 3D Hand Reconstruction 3D ViTs

Mar 15, 2026

RegFormer++: An Efficient Large-Scale 3D LiDAR Point Registration Network with Projection-Aware 2D Transformer

Although point cloud registration has achieved remarkable advances in object-level and indoor scenes, large-scale LiDAR registration methods has been rarely explored before. Challenges mainly arise from the huge point scale, complex point distribution, and numerous outliers within outdoor LiDAR scans. In addition, most existing registration works generally adopt a two-stage paradigm: They first find correspondences by extracting discriminative local descriptors and then leverage robust estimators (e.g. RANSAC) to filter outliers, which are highly dependent on well-designed descriptors and post-processing choices. To address these problems, we propose a novel end-to-end differential transformer network, termed RegFormer++, for large-scale point cloud alignment without requiring any further post-processing. Specifically, a hierarchical projection-aware 2D transformer with linear complexity is proposed to project raw LiDAR points onto a cylindrical surface and extract global point features, which can improve resilience to outliers due to long-range dependencies. Because we fill original 3D coordinates into 2D projected positions, our designed transformer can benefit from both high efficiency in 2D processing and accuracy from 3D geometric information. Furthermore, to effectively reduce wrong point matching, a Bijective Association Transformer (BAT) is designed, combining both cross attention and all-to-all point gathering. To improve training stability and robustness, a feature-transformed optimal transport module is also designed for regressing the final pose transformation. Extensive experiments on KITTI, NuScenes, and Argoverse datasets demonstrate that our model achieves state-of-the-art performance in terms of both accuracy and efficiency.

Jiuming Liu, Guangming Wang, Zhe Liu +7

School of Automation and Intelligent Sensing, State Key Laboratory of Avionics Integration and Aviation System-of-Systems Synthesis, Shanghai Jiao Tong University, Shanghai 200240, China. · Department of Engineering, University of Cambridge, UK. · China University of Mining and Technology. +4

Point Cloud Registration 3D ViTs