3D Scene Understanding

Follow this topic Ask about this topic

Momentum

27 papers in the last four weeks, up 200% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 188

All topics

LetOccVote: Learning Weakly Supervised 3D Occupancy through Consensus
Sep 4, 2026Chi Zhang, Qi Song, Feifei Li +23D Occupancy Prediction Pseudo-Labeling
Tsinghua University · Shenzhen Polytechnic University
GraFT: A Training-Free Framework for Spatial Reasoning in Multimodal Large Language Models via 3D Scene Graphs
Sep 3, 2026Junqing Du, Fernando Ropero, Erkin Turkoz +23D Spatial Reasoning Multimodal Large Language Models
Riemann Lab, Huawei Technologies
Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving
Aug 31, 2026Xin Zhou, Zongchuang Zhao, Zhibo Yang +13VLMs for Autonomous Driving Autonomous Driving Perception
Qwen Team, Huazhong University of Science and Technology
OVIP-SG: Open-Vocabulary Instance-Preserving Scene Graphs for Mapping and Retrieval of Small, Fine-Grained Objects
Aug 18, 2026Tianjing Hao, Haiyu Lan, Angsong Li +63D SGG 3D Scene Understanding
1Xi’an Jiaotong University · 2AgiBot
Geometry-Grounded Unified 3D Perception for Autonomous Driving
Aug 13, 2026Longfei Xu, Xiaohui Wang, Zehao Huang +4Depth Estimation Autonomous Driving Perception
School of Computer Science and Engineering Beihang University Beijing, China · School of Computer Science Beijing University of Posts and Telecommunications Beijing, China · School of Artificial Intelligence Beihang University Beijing, China
STAR: A Spatial-Topology Aware Routing Framework for Generalizable 3D Scene Understanding
Aug 12, 2026Mingwei Xing, Xinliang Wang, Yifeng ShiSparse Mixture-of-Experts Domain Generalization
KE Holdings Inc.
ThinkAfford: Affordance-Centric Reasoning for Fine-Grained 3D Grounding in Cluttered Scenes
Aug 11, 2026Xinrui Lin, Sha Zhang, Shumin Wang +33D Scene Understanding 3D VLMs
University of Science and Technology of China, Hefei, China · The Chinese University of Hong Kong, Hong Kong SAR, China
LEGO: Leveled Language Gaussian Splatting
Aug 10, 2026Yuning Peng, Haiping Wang, Yuan Liu +33D Gaussian Splatting Visual Spatial Reasoning
Wuhan University · Hong Kong University of Science and Technology
RoboSeg: Online Part-Level Semantic Reconstruction for Robotic Manipulation via a Single Eye-in-Hand Camera
Aug 10, 2026Zhaochen Lan, Mengxiang LinRobotic Grasping 3D Part Segmentation
School of Mechanical Engineering and Automation, Beihang University, Beijing 100191, China
RayLift: Lifting Complementary Ray-Wise Evidence with 3D Geometry Priors for Semantic Scene Completion
Aug 9, 2026Meng Wang, Hongxia Yu, Wenzhe He +43D Semantic Segmentation 3D Scene Completion
College of Computer Science and Electronic Engineering,Hunan University,Changsha,China
Rethinking 3D Segmentation from Individual LiDAR Scans: Incidence-Aware Sampling on the SIP Benchmark
Aug 7, 2026Seongyong Kim, Jingdao Chen, Yong Kwon Cho3D Point Cloud Segmentation 3D Semantic Segmentation
Graduate Student, School of Civil and Environmental Engineering, Georgia Institute of Technology, 790 Atlantic Dr., Atlanta GA · Assistant Professor, Department of Computer Science and Engineering, Mississippi State University, 665 George Perry St, Mississippi State, MS 39762 · Professor, School of Civil and Environmental Engineering, Georgia Institute of Technology, 790 Atlantic Dr., Atlanta, GA
CANIS: Generation-Assisted 3D Canonicalization via an Image-Semantic Bridge
Aug 7, 2026Kendong Liu, Yuxin Yao, Junhui Hou3D Scene Understanding
The authors are with the Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China
InstanceSplat: Instance-Aware Feed-Forward 3D Gaussian Splatting for Scene Understanding
Aug 7, 2026Minchao Jiang, Xiaoxuan Ma, Shunyu Jia +33D Gaussian Splatting Open-Vocabulary 3D Segmentation
1Shanghai Jiao Tong University · 2Eastern Institute of Technology, Ningbo · 3Carnegie Mellon University +2
UQ-Loc: Uncertainty-Aware LiDAR Scene Coordinate Regression
Aug 6, 2026Jacek KomorowskiUncertainty Quantification LiDAR Localization
Warsaw University of Technology, Warsaw, Poland
Prior-SG: Task and Prior Driven Region Segmentation for Scene Graphs in Arbitrarily-Structured Environments
Aug 6, 2026Giorgio Tonetti, Laurent Kneip, Abel Gawel +1Open-Vocabulary 3D Segmentation Markov Random Fields
RAI Institute · ETH Zurich
Iterate or Widen? When Test-Time Refinement Helps LiDAR Scene Completion: A Controlled Study of Evidence Geometry, Training Coverage, and Compute
Aug 6, 2026Shijie Hao, Weining Zhang3D Semantic Segmentation 3D Scene Completion
Phillips Exeter Academy · Cheung Kong Graduate School of Business
SmartMage: Dynamic Modality Orchestration for 3D Scene Understanding
Aug 5, 2026Yue Zhang, Yingzhao Jian, Yunqiu Xu +2Mixture of Experts Multimodal Large Language Models
Zhejiang University Hangzhou, Zhejiang, China · Stanford University Stanford, California, USA
Disentangling 3D Modeling from Spatial Reasoning
Aug 5, 2026Haoze Sun, Jiequan Cui, Qingshan Xu +13D Spatial Reasoning 3D Scene Understanding
HFUT · USTC
HiSC: Hierarchical Spatial Clustering Token Compression for Efficient 3D Scene Understanding
Aug 5, 2026Jiuhe Qu, Yingping Liang, Ying Fu3D Spatial Reasoning Visual Token Pruning
Beijing Institute of Technology Beijing, China
OutLangSplat: 3D Language Gaussian Splatting for UAV Outdoor Scenes
Aug 5, 2026Xia Yan, He Wu, Yanghui Xu +23D Gaussian Splatting Language-Embedded 3DGS
Zhejiang University of Technology · Hangzhou Dianzi University
Geospatial-Prior Guidance for 3D Semantic Scene Completion
Aug 4, 2026Meng Wang, Shougao Zhang, Wenzhe He +43D Occupancy Prediction 3D Shape Completion
College of Computer Science and Electronic Engineering, Hunan University, Hunan, China
PolyLayout: Multi-room Manhattan Layout Estimation
Aug 4, 2026Gustav Hanning, Shaohui Liu, Rémi Pautrat +33D Scene Understanding
Lund University · ETH Zurich · Microsoft Spatial AI Lab
Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding
Aug 4, 2026Lucy Lin, Ayush Jain, Yifan Liu +13D Foundation Models 3D VQA
Carnegie Mellon University
Assistant Placement Aria: A Benchmark for Egocentric Placement Assistance
Aug 1, 2026Amir Belder, Gonçalo Dias Pais, Refael Vivanti +5Robot Manipulation Benchmarks 3D Scene Understanding
Reality Labs, Meta inc. and Technion, institute of technology · Sensei, Lisbon, Portugal · Reality Labs, Meta inc. +1
Distill What RGB Can Recover: Privileged 3D Evidence for RGB-Only Vision-Language Models
Jul 31, 2026Yanbin Hu, Jin Cui, Jun Ye +43D Spatial Reasoning VLM Distillation
School of Software, Xi’an Jiaotong University · School of Artificial Intelligence, Xi’an Jiaotong University · State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University +1
MonoVoc: Decoupling Geometry and Semantics for Lightweight Monocular Open-Vocabulary 3D Gaussians
Jul 30, 2026Pouya Ardekhani, Zahra Dehghanian, Morteza Abolghasemi +13D Gaussian Splatting Open-Vocabulary 3D Segmentation
Sharif University of Technology, Tehran, Iran
SpatialQ: Understanding 3D Gaussian Splatting Scene Quality via Visual-based MLLM
Jul 29, 2026Jingxuan Su, Shenglin Wang, Tiesong Zhao +23D Gaussian Splatting 3D Scene Understanding
Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, School of Electronic and Computer Engineering, Peking University, Shenzhen 518055, China · Peng Cheng Laboratory, Shenzhen, 518055, China · College of Physics and Information Engineering, Fuzhou University, Fuzhou 350108, China
SceneActBench: Can Agents Act on the 3D Scenes They See?
Jul 24, 2026Yifei Zhao, Xiangxin Zhou, Wenhao Yang +11AI Agent Benchmarks Tool-Using Vision-Language Agents
1Tencent Hunyuan · 2THU · 3NJU +3
Unified Video Dense Prediction from Disjoint Data
Jul 23, 2026Yihong Sun, Seoung Wug Oh, Jiahui Huang +2Multi-Task Learning Dense Prediction
Adobe Research · Cornell University
Scene Parameter Saliency via Differentiable Light Transport
Jul 23, 2026Linas Beresna, Eugene FiumeGradient-Based Attribution 3D Scene Understanding
Simon Fraser University Burnaby, Canada

Sep 4, 2026, cs.CVJ/K move · Enter open · S save

LetOccVote: Learning Weakly Supervised 3D Occupancy through Consensus

Chi Zhang, Qi Song, Feifei Li, Jie Li+1

Tsinghua University · Shenzhen Polytechnic University

3D Occupancy Prediction Pseudo-Labeling 3D Scene Understanding

Open paper AskPDF arXiv

Weakly supervised 3D occupancy prediction reduces the reliance on costly 3D annotations by learning from 2D pseudo-labels generated by vision foundation models. However, existing methods typically use these imperfect pseudo-labels directly as supervision, making occupancy learning vulnerable to erroneous geometric and semantic targets. We observe that agreement across repeated observations provides an inexpensive and reliable cue for assessing pseudo-label reliability. Based on this observation, we propose \textbf{LetOccVote}, a weakly supervised Gaussian-based occupancy framework that leverages cross-frame voting to improve both geometric and semantic supervision. For geometry, Depth Vote exploits cross-frame geometric agreement to refine supported pseudo depth and reject contradictory estimates before volumetric lifting and depth supervision. For semantics, Semantic Vote aggregates pseudo-semantic observations in a shared 3D space to identify reliable and contested evidence, strengthening reliable semantic supervision while filtering unreliable pseudo-label segments. The entire framework is trained solely with 2D pseudo-label supervision without requiring 3D occupancy annotations. On Occ3D-nuScenes, LetOccVote achieves 53.27 IoU and 20.39 mIoU, establishing state-of-the-art performance among methods with 2D pseudo-label supervision.

Momentum

Related topics

Latest papers 188