Scene Understanding

Ask about this topic

Momentum

26 papers in the last four weeks, up 73% on the four weeks before. 0.3% of all new papers.

Jul 6Week of Sep 21
View on map

Latest papers 220

All topics
CardsList

  1. TBSG-Net: Temporal Bipartite Scene Graph Network for Fine-Grained Video Moment Retrieval

    Aug 3, 2026Ji Huang, Yongsheng Dai, Tianyu Ren +2Video Temporal GroundingSpatio-Temporal Scene Graphs

    School of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast, Belfast, Northern Ireland · Discovery AI Lab the NI Landscape Partnership in AI for Bioscience at the School of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast, Belfast, Northern Ireland

  2. DynActiveGS: Active Gaussian Splatting for Dynamic Scene Reconstruction

    Aug 2, 2026Hongbo Duan, Pengting Luo, Chengzhi Zhao +3Scene ReconstructionDynawm

    Tsinghua University, Shenzhen International Graduate School Shenzhen, Guangdong, China · Huawei Technologies Ltd Shenzhen, Guangdong, China · Harbin Institute of Technology, Shenzhen Shenzhen, Guangdong, China +1

  3. SIPTraj: Map-Free End-to-End Trajectory Prediction via Physics-Guided Scene Interaction

    Aug 1, 2026Feifei Liu, Zejun Wei, Haozhe Wang +6Autonomous DrivingScene Understanding

    School of Data Science and Engineering, Xingzhi College, South China Normal University, Shanwei, 516600, China · Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology, Hong Kong, China · University of Macau, Macau, China +2

  4. OSEF: One-Step Evidence Fusion for Cross-Video Scene Procedure Planning

    Jul 31, 2026Zhentong Ye, Lei Zhang, Sijia Zhou +7Scene UnderstandingEvidence Fusion

  5. CorrelationFlow: A Training-Free Geometric Approach for LiDAR Scene Flow Estimation

    Jul 31, 2026Minh-Quan Dao, Yancong Lin, Julie Stephany Berrio Perez +1Optical FlowLidar

    Nantes Université · University of Nottingham · University of Queensland +1

  6. One Patch Is Enough: Reinforcement-Optimized Visual Token Grounding for MLLM-Based Scene Text Spotting

    Jul 30, 2026Rui Tang, Wentao Yang, Peirong Zhang +4Scene Text RecognitionVision-Language Model Grounding

    South China University of Technology · Guangzhou, China · HiThink Research +1

  7. Endo-NeRF++: Uncertainty-Aware Neural Rendering with Multi-Resolution Hash Encoding for Dynamic Surgical Scene Reconstruction

    Jul 30, 2026Gousia Habib, Laura RuotsalainenNeural RenderingScene Understanding

    Department of Computer Science, University of Helsinki, Finland

  8. DensFiLM: Density-Conditioned Video Saliency for Crowd Scenes

    Jul 28, 2026Anis Ur RahmanSaliencyDense Prediction

    CSC - IT Center for Science Ltd., Espoo, Finland

  9. Out-of-Length Scene Text Recognition: A Two-Axis Diagnosis and a Training-Free Fix

    Jul 25, 2026Zobeir Raisi, John ZelekScene Text RecognitionCharacter Error Rate

    aElectrical Engineering Department, Chabahar Maritime University, Chabahar, Iran · bDepartment of Systems Design Engineering, University of Waterloo, Waterloo, N2L 3G1, ON, Canada

  10. SceneActBench: Can Agents Act on the 3D Scenes They See?

    Jul 24, 2026Yifei Zhao, Xiangxin Zhou, Wenhao Yang +113D Scene UnderstandingScene Understanding

    1Tencent Hunyuan · 2THU · 3NJU +3

  11. Geometric 2D Scene Graph Generation

    Jul 24, 2026Christoph Jahn, Urs Waldmann, Bastian GoldlueckeInterleaved Graph AttentionScene Understanding

    1Mercedes-Benz AG, Sindelfingen, Germany · Department of Computer and Information Science, University of Konstanz, Konstanz, Germany

  12. Scene Parameter Saliency via Differentiable Light Transport

    Jul 23, 2026Linas Beresna, Eugene FiumeSaliencyDifferentiable Rendering

    Simon Fraser University Burnaby, Canada

  13. SeededGrasp: Language-Guided Grasping in Complex Scenes with Multiple Embodiments

    Jul 22, 2026Yang Xu, Gurpreet Singh Mukker, Raymond Wang +3Robotic GraspingGrasp Adaptation

    University of Toronto · Vector Institute · University of British Columbia +1

  14. D3VL: Understanding Driving Scenes from 3D Time Series Data and Video with Language Models

    Jul 21, 2026Heesang Han, A. Lynn Abbott, Abhijit SarkarAutonomous DrivingWaymo Open Motion Dataset

    Bradley Department of Electrical and Computer Engineering, Virginia Tech, USA · Sanghani Center for Artificial Intelligence and Data Analytics, USA · Virginia Tech Transportation Institute, USA

  15. CR-Refiner: An Object-Centric Optimal Transport Reranker for Edit-Conditioned 3D Scene Retrieval

    Jul 21, 2026Hao Wu, Jinjing Zhu, Nanyu Wu +43D Editing3D Scene Understanding

    Hong Kong University of Science and Technology · Hong Kong University of Science and Technology (Guangzhou)

  16. Plenoptic Condensation: A Novel Approach to Generalized Scene Reconstruction

    Jul 20, 2026Brevin Tilmon, Alex DeJournett, John Leffingwell +1Scene ReconstructionScene Understanding

    Quidient, Columbia, MD

  17. Splat-based 3D Scene Reconstruction with Extreme Motion-blur

    Jul 18, 2026Hyeonjoong Jang, Dongyoung Choi, Donggun Kim +23D ReconstructionRgb-Depth Cameras

    KAIST · HYPERGRAM

  18. Scene-SAM3D: Multi-View Scene Asset Generation Without Fine-Tuning

    Jul 18, 2026Yuqi Zhang, Yadan Luo, Xiangyu Sun +33D Scene GenerationIndoor Scene Generation

    The University of Queensland · Shanghai AI Laboratory · East China Normal University

  19. DORS: Dynamic Attention Routing for Diffusion-based Object Removal in Dense Scenes

    Jul 18, 2026Haitong Tang, Haipeng Liu, Yang WangVideo Object RemovalRemoval

    School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China

  20. Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation

    Jul 16, 2026Chi Kit Wong, Ye Pan, Yuanhuiyi Lyu +6Egocentric VisionMultimodal Large Language Models

    The Hong Kong University of Science and Technology (Guangzhou) · Guangxi Zhuang Autonomous Region Information Center · The Hong Kong University of Science and Technology

  21. Instant NuRec: Feed-Forward 3D Gaussian Reconstruction for Driving Scene Simulation

    Jul 15, 2026NVIDIA, :, Jiahui Huang +14Autonomous DrivingCamera

    NVIDIA†

  22. PUF: Plug-and-Play Uncertainty-Aware Fusion for Online 3D Scene Graph Generation

    Jul 8, 2026Yi Yang, Myrna Castillo, Bodo Rosenhahn +13D Scene GraphsUncertainty-Aware Fusion

    Leibniz Universität Hannover, Germany · Istituto Italiano di Tecnologia, Italy · University of Bath, UK

  23. PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space

    Jul 6, 2026Sensen Gao, Zhaoqing Wang, Qihang Cao +33D Scene Generation3D Representation

    Nanyang Technological University · AISphere

  24. Beyond Isolated Objects: Relationship-aware Open Vocabulary Scene Understanding via 3D Scene Graph Analysis

    Jul 6, 2026Xianhao Chen, Jiarui Hu, Yuanbo Yang +53D Scene Understanding3D Scene Graphs

    State Key Lab of CAD&CG, Zhejiang University, China · Zhejiang University, China

  25. DeGenseGS: Geometrically and Semantically Decoupled Surgical Scene Understanding in 4D Gaussian Splatting

    Jul 6, 2026Yimo Wang, Bin Kang, Shuojue Yang +14D ReconstructionDeformable Cnn

    School of Automation, Southeast University, Nanjing 210096, China · Department of Biomedical Engineering, National University of Singapore, Singapore · School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China

  26. Learning to Generate Multiple Objects from Dense and Occluded Layouts

    Jul 3, 2026Bach-Hoang Ngo, Si-Tri Ngo, Hieu Le +1Diverse Occlusion-And-Revelation ScenariosScene Reasoning

    University of Science, Ho Chi Minh City, Vietnam · 2Vietnam National University, Ho Chi Minh City, Vietnam · 3UNC Charlotte, North Carolina, United States

  27. Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments

    Jul 2, 2026Xianhui Meng, Zirui Song, Yuchen Zhang +103D Layout Generation3D Scene Generation

    University of Science and Technology of China · Xiaomi EV · Mohamed bin Zayed University of Artificial Intelligence +4

  28. InvSplat: Inverse Feed-Forward Scene Splatting

    Jul 2, 2026Polina Karpikova, Wenjing Bian, Haofei Xu +2Inverse RenderingFeed-Forward 3D Gaussian Splatting

    University of Tübingen, Tübingen AI Center · ETH Zurich

  29. Signal Structure-Aware Gaussian Splatting for Large-Scale Scene Reconstruction

    Jul 2, 2026Weiyi Xue, Fan Lu, Chi Zhang +6Scene ReconstructionTwo-Level Spatial-Frequency Fusion Strategy

    Tongji University · Beijing University of Technology · Johns Hopkins University +2

  30. Unified Panoramic-Gaussian Representation for Monocular 4D Scene Synthesis

    Jul 2, 2026Yuankun Yang, Yi Wei, Wenyang Zhou +1Omnidirectional ImagesCamera-Conditioned Video Generation

    School of Data Science, Fudan University · 2Central Media Technology Institute, Huawei

  31. Bridging 3D Gaussians and Semantic Occupancy for Comprehensive Open-Vocabulary Scene Understanding from Unposed Images

    Jul 2, 2026Hu Zhu, Bohan Li, Xianda Guo +53D GaussianVoxel

    Department of Computing, The Hong Kong Polytechnic University, Hong Kong, SAR, China · Eastern Institute of Technology, Ningbo, China · Shanghai Jiao Tong University, Shanghai, China +4

  32. NoPA: Non-Parametric Online 3D Scene Graph Generation

    Jul 1, 2026Qi Xun Yeo, Seungjun Lee, Yan Li +13D Scene Graphs3D Gaussian

    Department of Computer Science, National University of Singapore

  33. One Video, One World: Turning Monocular Video into Physical 4D Scenes

    Jun 30, 2026Junhao Chen, Boran Zhang, Mingjin Chen +7Monocular Video4D

    Shenzhen International Graduate School, Tsinghua University, China · University of Science and Technology of China, China · The Hong Kong Polytechnic University, China +4

  34. Seeing Through the Weights: Privacy Leakage in Scene Coordinate Regression

    Jun 30, 2026Oleksii Nasypanyi, Jaemin Cho, Utku Ozbulak +2Scene ReconstructionPrivacy

    Stony Brook University · Ghent University Global Campus · George Mason University Korea +1

  35. WaterGen: Decoupling Scene and Medium in Underwater Image Generation

    Jun 30, 2026Jiayi Wu, Tianfu Wang, Tianyi Xiong +6Indoor Scene GenerationScene Understanding

    University of Maryland · University of South Florida · University of Florida

  36. Hierarchical 3D Scene Graph Construction and Belief-based Planning for Semantic Navigation

    Jun 30, 2026Bing Wu, Zuyao Chen, Changwen ChenVision-Language NavigationLong-Horizon Planning

    The Hong Kong Polytechnic University

  37. Unveiling Transferability in Trajectory Prediction via Latent Scene Embeddings

    Jun 29, 2026Theodor Westny, David Axelsson, Björn Olofsson +1Human Motion PredictionCross-Dataset Benchmark

    Division of Vehicular Systems, Linköping University, Linköping, Sweden · Department of Automatic Control, Lund University, Lund, Sweden

  38. Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes

    Jun 29, 2026Xi Li, Linyuan Li, Yan Wu +43D ReconstructionLocal Camera Pose

    Realsee, China · Quanzhou University of Information Engineering, China

  39. Walking in the Implicit: Interactive World Exploration via Neural Scene Representation

    Jun 29, 2026Zhiqi Li, Chengrui Dong, Zhenhua Du +6Video World ModelsInteractive Video Generation

    Zhejiang University · Westlake University · Afari Intelligent Drive

  40. One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models

    Jun 28, 2026Xiaohao Xu, Feng Xue, Xiang Li +5Monocular Depth Estimation3D Foundation Models

    University of Michigan, Ann Arbor, MI, USA · Carnegie Mellon University, Pittsburgh, PA, USA · New York University, New York, NY, USA +1

  41. Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views

    Jun 28, 2026Mijin Yoo, In Cho, Subin Jeon +33D Scene UnderstandingNovel View Synthesis

    1Yonsei University · 2Seoul National University

  42. Panoramic Scene Understanding: A Survey from Distortion-Aware Engineering to Sphere-Native Modeling

    Jun 26, 2026Qinfeng Zhu, Lei FanOmnidirectional ImagesPanoptic Segmentation

    University of Liverpool, United Kingdom. · Xi’an Jiaotong-Liverpool University, China.

  43. Scene and Human in One World: Reconstruction in a Feedforward Pass

    Jun 26, 2026Boao Shi, Qiao Feng, Yiming Huang +1Human Mesh RecoveryMonocular Video

    University of Pennsylvania, Philadelphia, Pennsylvania, USA

  44. SAGE-Nav: Leveraging LLM Planning and Alignment Fusion for Hierarchical Scene Graph-Guided Navigation

    Jun 24, 2026Hao Su, Yuehao Huang, Yukai Ma +2Classical PlanningLarge Language Model Planning

    Zhejiang University, Hangzhou, China

  45. FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation

    Jun 23, 2026Orest Kupyn, Goutam Bhat, Philipp Henzler +3Feed-Forward 3D Gaussian SplattingSurface Representation

    1Google Research · University of Oxford, Visual Geometry Group · 3TU Munich

  46. OrbitForge: Text-to-3D Scene Generation via Reconstruction-Anchored Video Synthesis

    Jun 23, 2026Chenrui Fan, Paolo Favaro3D Scene GenerationScene Understanding

    Computer Vision Group, Institute of Computer Science University of Bern, Switzerland

  47. RoBoSR: Structured Scene Representations for Embodied Robotic Reasoning

    Jun 23, 2026Kewei Hu, Wanchan Yu, Fangwen Chen +6RobocasaSemantic Scene Understanding

  48. 4DVLT: Dynamic Scene Understanding with Worldline-Centered Vision-Language Tracking

    Jun 21, 2026Chaoyue Li, Boxue Yang, Shengyao Zhou +33D MotionScene Understanding

    Huazhong University of Science and Technology · Shanghai Jiao Tong University · Zhejiang University

  49. φφ-Scene: Physically Grounded Image-to-3D Scene Reconstruction

    Jun 19, 2026Haodong Li, Lulu Shao, Haolin Lu +4Scene Reconstruction3D Reconstruction

    University of California San Diego, USA

  50. 3D-DLP: Self-Supervised 3D Object-Centric Scene Representation Learning

    Jun 17, 2026Ellina Zhang, Madhaven Iyengar, Amir Zadeh +43D Scene Understanding3D Generation

    Carnegie Mellon University · Lambda AI

  51. Rethinking Text-to-Image as Semantic-Aware Data Augmentation for Indoor Scene Recognition

    Jun 17, 2026Trong-Vu Hoang, Quang-Binh Nguyen, Dinh-Khoi Vo +3Synthetic Image DetectionData Augmentation

    University of Science, VNU-HCM, Vietnam · Vietnam National University, Ho Chi Minh City, Vietnam

  52. BRDFusion: Physics Meets Generation for Urban Scene Inverse Rendering

    Jun 15, 2026Yi-Ruei Liu, Jie-Ying Lee, Zheng-Hui Huang +2Inverse RenderingRaymap-Induced Geometry

    National Yang Ming Chiao Tung University · University of Illinois Urbana-Champaign · National Taiwan University

  53. 3D Scene Graphs: Open Challenges and Future Directions

    Jun 15, 2026Dennis Rotondi, Francesco Argenziano, Sebastian Koch +103D Scene GraphsScene Understanding

    University of Stuttgart · IMPRS-IS · Sapienza University of Rome +7

  54. SceneCraft: Interactive System for Image Editing via Scene Graph

    Jun 15, 2026Duc-Manh Phan, Ngoc-Dai Tran, Duy-Khang Do +3Image EditingMulti-Reference Image Generation

    University of Science · Vietnam National University · University of Dayton

  55. PointDiffusion: Diffusion-Based Scene Completion in the Point Cloud Domain

    Jun 14, 2026Chidera Agbasiere, Mikhail Sannikov, Faith Ogunwoye +5Point CloudsDiffusion Models

    Intelligent Space Robotics Laboratory, Skolkovo Institute of Science and Technology, Moscow, Russia

  56. More with LESS -- Local Scene Representations for Tactile Imaging

    Jun 12, 2026Zohar Rimon, Elisei Shafer, Tal Tepper +4TactileSemantic Scene Understanding

    1Technion - Israel Institute of Technology · 2Rambam Health Care Campus

  57. MUSE: Agentic 3D Scene Authoring via Memory-Grounded Incremental Requirement Satisfaction

    Jun 12, 2026Ruijie Xu, Xinnan Zhu, Jiayu Ying +33D Scene GenerationScene Understanding

    1East China Normal University · 2Fudan University · 3Shanghai Jiao Tong University

  58. Occupancy-Grounded Room Segmentation for Hierarchical 3D Scene Graphs

    Jun 11, 2026Carlos Cueto Zumaya, Iacopo Catalano, Jorge Peña-Queralta +13D Scene Graphs3D Semantic Occupancy Prediction

    University of Turku, 20014 Turku, Finland · Centre for Artificial Intelligence, Zürich University of Applied Sciences, Winterthur, Switzerland

  59. Plan-and-Verify Video Reward Reasoning with Spatio-Temporal Scene Graph Grounding

    Jun 10, 2026Hyomin Kim, Junghye Kim, Joanie Hayoun Chung +4Text-To-Video Generation ModelSpatio-Temporal Scene Graphs

    Department of Artificial Intelligence, Korea University · Department of Statistics, Korea University

  60. SceneMiner: Identity-Preserving Multi-Task Fine-Tuning for Unified BEV Scene Mining

    Jun 9, 2026Abdalmalek Aburaddaha, Venkatraman Narayanan, Keval Thaker +1Scene ReasoningMulti--Task Learning

    University of Michigan-Dearborn 4901 Evergreen Rd Dearborn, MI 48128, USA