3D Object Understanding

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

23 new papers

A weekly snapshot of new work published in 3D Object Understanding.

Period ending 2026-09-14

19 new papers

A weekly snapshot of new work published in 3D Object Understanding.

Period ending 2026-09-07

41 new papers

A weekly snapshot of new work published in 3D Object Understanding.

Inside this field

Focused directions

Focused topic

3D Object Understanding

Within 3D Object Understanding

439 papersExplore

Focused topic

3D Scene Understanding

Within 3D Object Understanding

102 papersExplore

Focused topic

Real3D-Ad Datasets

Within 3D Object Understanding

88 papersExplore

Focused topic

3D Perception

Within 3D Object Understanding

50 papersExplore

Focused topic

3D Geometry

Within 3D Object Understanding

42 papersExplore

Focused topic

3D Models

Within 3D Object Understanding

38 papersExplore

Focused topic

3D Representation

Within 3D Object Understanding

34 papersExplore

722 papers

Latest in 3D Object Understanding

Browse all topics →

HAD: Hallucination-Aware Diffusion Priors for 3D Reconstruction
May 16, 2026Xi Liu, Weiwei Sun, Zhou Ren +33D Reconstruction Novel View Synthesis
3DPhysVideo: Consistency-Guided Flow SDE for Video Generation via 3D Scene Reconstruction and Physical Simulation
May 16, 2026Hwidong Kim, Yunho Kim, Tae-Kyun Kim3D Generative Models 3D Reconstruction
VolTA-3D: Self-Supervised Learning for Brain MRI using 3D Volumetric Token Alignment
May 16, 2026Amy Makawana, Abhijeet Parida, Marius George Linguraru +2Brain Magnetic Resonance Imaging 3D Semantic Segmentation
EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformers
May 16, 2026Zongyuan Yang, Mingjing Yi, Wanli Ma +83D Generative Models 3D Object Understanding
IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation
May 15, 2026Yuqi Wu, Tianyu Hu, Wenzhao Zheng +43D Geometry Multi-View
Unlocking Dense Metric Depth Estimation in VLMs
May 15, 2026Hanxun Yu, Xuan Qu, Yuxin Wang +2Ava-Vlm Depth Estimation
Cross-Modal Registration Between 3D and 2D Fingerprints via Pose-Aware Unwrapping and Point-Cloud Fusion
May 15, 2026Xiongjun Guan, Jianjiang Feng, Jie ZhouImage Registration Fingerprint
Hierarchical and Holistic Open-Vocabulary Functional 3D Scene Graphs for Indoor Spaces
May 15, 2026Xinggang Hu, Chenyangguang Zhang, Alexandros Delitzas +43D Scene Graphs 3D Object Understanding
Parameter Efficient Multi-Class Intelligent Scheduling for Multimodal Online Distributed Industrial Anomaly Detection
May 15, 2026Heqiang Wang, Weihong Yang, Zheyuan Yang +4Zero-Shot Anomaly Detection Anomaly Detection
3D Segmentation Using Viewpoint-Dependent Spatial Relationships
May 15, 2026Ayaka Nanri, Klara Reichard, Mert Kiray +33D Semantic Segmentation 3D Scene Understanding
3DEditSafe: Defending 3D Editing Pipelines from Unsafe Generation
May 14, 2026Nicole Meng, Zheyuan Liu, Meng Jiang +13D Editing 3D Object Understanding
Discretizing Group-Convolutional Neural Networks for 3D Geometry in Feature Space
May 14, 2026Daniel Franzen, Jean Philip Filling, Michael WandGeometric Deep Learning Feature Space
SAGE3D: Soft-guided attention and graph excitation for 3D point cloud corner detection
May 14, 2026Batuhan Arda Bekar, Can Sarı, Hüseyin Can Gülkan +1Light Detection And Ranging Point Clouds 3D Object Detection
3D Skew-Normal Splatting
May 14, 2026Xiangru Wu, Ke Fan, Yanwei FuNovel View Synthesis 3D Priors
Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image
May 14, 2026Ming Qian, Zimin Xia, Changkun Liu +63D Scenes 3D Object Understanding
Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model
May 14, 2026Tao Lin, Yuxin Du, Jiting Liu +14Efficient Vision-Language-Action Models Vision-Language-Action Models
Exploring Bottlenecks in VLM-LLM Navigation: How 3D Scene Understanding Capability Impacts Zero-Shot VLN
May 14, 2026Ziyi Xia, Chaoran Xiong, Litao Wei +2Vision-Language Navigation 3D Scene Understanding
Beyond Instance-Level Self-Supervision in 3D Multi-Modal Medical Imaging
May 14, 2026Tan Pan, Shuhao Mei, Yixuan Sun +8Multimodal Pretraining Medical Imaging
Towards Accurate Single Panoramic 3D Detection: A Semantic Gaussian Centric Approach
May 14, 2026Kanglin Ning, Yiran Zhao, Wenrui Li +33D Object Detection 3D Gaussian
From Sparse to Dense: Spatio-Temporal Fusion for Multi-View 3D Human Pose Estimation with DenseWarper
May 14, 2026Ling Li, Changjie Chen, Yuyan Wang +43D Pose Estimator 3D Perception
A3D: Agentic AI flow for autonomous Accelerator Design
May 14, 2026Abinand Nallathambi, Christopher Knight, Shantanu Ganguly +2Accelerator High-Level Synthesis
SToRe3D: Sparse Token Relevance in ViTs for Efficient Multi-View 3D Object Detection
May 13, 2026Sandro Papais, Lezhou Feng, Charles Cossette +13D Object Detection 3D Object Understanding
Sparse Code Uplifting for Efficient 3D Language Gaussian Splatting
May 13, 2026Lovre Antonio Budimir, Yushi Guan, Steve Ryhner +23D Gaussian Splats 3D Gaussian
Uncertainty-Aware 3D Position Refinement for Multi-UAV Systems
May 13, 2026Hosam Alamleh, Damir PulatovDrone-View Geo-Localization Multi-Uav Systems
Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation
May 13, 2026Nikitas Chatzis, Marios Loizou, Evangelos Kalogerakis3D Assets 3D Generative Models
HarmoGS: Robust 3D Gaussian Splatting in the Wild via Conflict-Aware Gradient Harmonization
May 13, 2026Yulei Kang, Tianze Zhu, Jian-Fang Hu +23D Gaussian Splats 3D Gaussian
OCH3R: Object-Centric Holistic 3D Reconstruction
May 13, 2026Yi Du, Yang You, Xiang Wan +13D Reconstruction Feed-Forward 3D Reconstruction
AssemblyBench: Physics-Aware Assembly of Complex Industrial Objects
May 13, 2026Danrui Li, Jiahao Zhang, Bernhard Egger +43D Models Manufacturing
Optimizing 4D Wires for Sparse 3D Abstraction
May 12, 2026Dong-Yi Wu, Tong-Yee Lee3D Geometry Differentiable Rendering
Rainbow Deep Q-Learning with Kinematics-Aware Design for Cooperative Delta and 3-RRS Parallel Robot Insertion
May 12, 2026Hassen Nigatu, Gaokun Shi, Jituo Li +2Deep Q-Networks Kinematics
Grounding by Remembering: Cross-Scene and In-Scene Memory for 3D Functional Affordances
May 12, 2026Qirui Wang, Jingyi He, Yining Pan +2Affordances Large Vision Language Models
3D-Belief: Embodied Belief Inference via Generative 3D World Modeling
May 12, 2026Yifan Yin, Zehao Wen, Suyu Ye +103D World 3D Scenes
Lite3R: A Model-Agnostic Framework for Efficient Feed-Forward 3D Reconstruction
May 12, 2026Haoyu Zhang, Zeyu Zhang, Zedong Zhou +2Feed-Forward 3D Reconstruction 3D Object Understanding
Forecast-aware Gaussian Splatting for Predictive 3D Representation in Language-Guided Pick-and-Place Manipulation
May 11, 2026Kaixin Jia, Jiacheng XuReal-World Manipulation Tasks Manipulation
Pixal3D: Pixel-Aligned 3D Generation from Images
May 11, 2026Dong-Yang Li, Wang Zhao, Yuxin Chen +53D Generation 3D Assets
BenchCAD: A Comprehensive, Industry-Standard Benchmark for Programmatic CAD
May 11, 2026Haozhe Zhang, Kaichen Liu, Miaomiao Chen +4Text-To-Cad Computer-Aided Design
Predicting 3D structure by latent posterior sampling
May 11, 2026Azmi Haider, Dan Rosenbaum3D Latent Diffusion Model 3D Reconstruction
Rapid Forest Fuel Load Estimation via Virtual Remote Sensing and Metric-Scale Feed-Forward 3D Reconstruction
May 11, 2026Quanyun Wu, Kyle Gao, Wentao Sun +6Forest Inventory Canopy
GemDepth: Geometry-Embedded Features for 3D-Consistent Video Depth
May 11, 2026Yuecheng Liu, Junda Cheng, Longliang Liu +43D Perception Large Inter-Frame Displacements
VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models
May 11, 2026Hao Wang, Xiaobao Wei, Jingyang He +10Spatial Grounding Vision-Language Model Grounding
PC3D: Zero-Shot Cooperation Across Variable Rosters via Personalized Context Distillation
May 11, 2026Ahmet Onur Akman, Rafał KucharskiMulti-Agent Reinforcement Learning Multi-Robot Systems
MTA-RL: Robust Urban Driving via Multi-modal Transformer-based 3D Affordances and Reinforcement Learning
May 11, 2026Guangli Chen, Dianzhao Li, Wenjian Zhong +2Autonomous Driving 3D Scene Understanding
MUSDA: Multi-source Multi-modality Unsupervised Domain Adaptive 3D Object Detection for Autonomous Driving
May 11, 2026Xiaohu Lu, Hamed Khatounabadi, Hayder Radha3D Object Detection Autonomous Driving Perception
BEA-GS: BEyond RAdiance Supervision in 3DGS for Precise Object Extraction
May 10, 2026Alessio Mazzucchelli, Maria Naranjo-Almeida, Jorge Bustos-Sanchez +43D Gaussian Splats 3D Semantic Segmentation
FrameTwin: Curve-Anchored Gaussian Alignment from Sparse Views for Adaptive Wireframe 3D Printing
May 10, 2026Wenting Wang, Zhuo Huang, Kun Qian +5Full Deformable Mesh State Additive Manufacturing
Curvature-Aware Captioning:Leveraging Geodesic Attention for 3D Scene Understanding
May 9, 2026Ziyao He, Yingjie Liu, ZhangYangRui +33D Scene Understanding Curvature-Aware Quadratic Banks
ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting
May 9, 2026Luchao Wang, Kaimin Liao, Qian Ren +33D Gaussian Splats 3D Object Understanding
MicroDiffuse3D: A Foundation Model for 3D Microscopy Imaging Restoration
May 8, 2026Yongkang Li, Brian Wong, King Wai Chiu +5Image Restoration Microscopy
123D: Unifying Multi-Modal Autonomous Driving Data at Scale
May 8, 2026Daniel Dauner, Valentin Charraut, Bastian Berle +10Naturalistic Driving Data Autonomous Driving
Generative 3D Gaussians with Learned Density Control
May 8, 2026Runjie Yan, Yan-Pei Cao, Peng Wang +23D Gaussian Generative Models
Proxy3D: Efficient 3D Representations for Vision-Language Models via Semantic Clustering and Alignment
May 8, 2026Jerry Jiang, Haowen Sun, Denis Gudovskiy +43D Scene Understanding 3D Representation
Seeing Across Skies and Streets: Feedforward 3D Reconstruction from Satellite, Drone, and Ground Images
May 8, 2026Qiwei Wang, Zhongyao Tuo, Xianghui Ze +1Feed-Forward 3D Reconstruction Cross-View
DVD: Discrete Voxel Diffusion for 3D Generation and Editing
May 8, 2026Zhengrui Xiang, Jiaqi Wu, Fupeng Sun +23D Latent Diffusion Model Voxel
Mind the Gap: Geometrically Accurate Generative Reconstruction from Disjoint Views
May 8, 2026Grzegorz Wilczynski, Mikołaj Zielinski, Bartosz Świrta +23D Perception
Distill, Diffuse, and Semanticize (DDS): Annotation-Free 3D Scene Understanding Based on Multi-Granularity Distillation and Graph-Diffusion-Based Segmentation
May 8, 2026Yijing Wang, Ruonan Li, Qilin Wang +23D Scene Understanding 3D Object Understanding
Velocity-Space 3D Asset Editing
May 8, 2026Hao Liu, Yuxuan Lin, Jingfeng Guo +43D Editing 3D Assets
SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis
May 8, 2026Yecong Wan, Fan Li, Mingwen Shao +1Novel View Synthesis 3D Gaussian Splatting
Real-IAD MVN: A Multi-View Normal Vector Dataset and Benchmark for High-Fidelity Industrial Anomaly Detection
May 8, 2026Wenbing Zhu, Jianing Liang, Linjie Cheng +7Real3D-Ad Datasets Multi-View
Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models
May 8, 2026Haoming Wang, Wei GaoSpatial Reasoning 3D Representation
AGA3DNet: Anatomy-Guided Gaussian Priors with Multi-view xLSTM for 3D Brain MRI Subtype Classification
May 8, 2026Peiyu Duan, Xueqi Guo, Sepehr Farhand +5Anatomical Priors Anatomy

May 16, 2026 · cs.CVJ/K move · Enter open · S save

HAD: Hallucination-Aware Diffusion Priors for 3D Reconstruction

Xi Liu, Weiwei Sun, Zhou Ren, Chris Broaddus+2

1Amazon AWS · 2Clemson University

Diffusion priors have recently demonstrated strong capability in enhancing the quality of sparse-view 3D reconstruction by augmenting training views at novel viewpoints, but they inevitably introduce hallucinated content -- artifacts inconsistent with the input views -- into the final 3D model. To address this challenge, we propose Hallucination-Aware Diffusion prior (HAD), which estimates pixel-wise hallucination score maps for augmented images by leveraging multi-view reasoning capabilities from a feedforward novel view synthesis (NVS) network pre-trained on large-scale 3D data. These hallucination scores enable selective masking of unreliable pixels during the progressive 3D reconstruction procedure, preventing the introduction of non-existent artifacts into the 3D model. To further enhance performance, we create multiple versions of augmented images at each novel view by conditioning the diffusion prior on different input views, which are then fused into a final image that leverages the broader context across all input views. We show that our method substantially reduces hallucination artifacts in diffusion-assisted 3D reconstruction, thereby achieving state-of-the-art performance across multiple benchmarks on novel view synthesis. Our project are publicly available at \href{https://xiliu8006.github.io/HAD-Project-website/}{project website}.

3D Reconstruction Novel View Synthesis Diffusion Priors 3D Object Understanding Pixel-Level Prediction Hallucinations

Open paper Ask about it PDF