3D Scene Representation

Ask about this topic

Overview

3D scene representation studies how to encode the shape, appearance, meaning, and motion of environments so they can be reconstructed, rendered, edited, or used by robots and other AI systems. Common approaches include explicit representations such as meshes, voxels, point clouds, Gaussian splats, and scene graphs, alongside implicit neural fields and compact learned tokens; these are used in tasks from novel-view synthesis to dynamic mapping and scene generation. Current work increasingly combines geometric structure with language or semantic features, and tests representations on reconstruction benchmarks as well as navigation, spatial reasoning, and manipulation tasks. A central tension is balancing visual fidelity and geometric reliability against memory, computation, and scalability, especially for large, changing scenes and incomplete observations.

Latest papers

CardsList

242 papers35 papers in the last four weeks, up 35% on the four weeks before. 0.2% of all new papers.

  1. RenderMem: Rendering as Spatial Memory Retrieval

    Mar 15, 2026JooHyun Park, HyeongYeop KangLong-Term Memory for Embodied AgentsAgent Memory

    Korea University, South Korea

  2. Contextual Graph Representations for Task-Driven 3D Perception and Planning

    Mar 12, 2026Christopher AgiaRobot Task PlanningGraph-Based Planning

  3. Radiometric fingerprinting of object surfaces using mobile laser scanning and semantic 3D road space models

    Mar 11, 2026Benedikt Schwab, Thomas H. KolbeRemote Sensing3D Scene Representation

    Chair of Geoinformatics, TUM School of Engineering and Design, Technical University of Munich, Arcisstraße 21, Munich, 80333, Germany

  4. LiTo: Surface Light Field Tokenization

    Mar 11, 2026Jen-Hao Rick Chang, Xiaoming Zhao, Dorian Chan +13D Representation Learning3D Scene Representation

    Apple

  5. Implicit Geometry Representations for Vision-and-Language Navigation from Web Videos

    Mar 10, 2026Mingfei Han, Haihong Hao, Liang Ma +6Vision-Language Navigation3D Scene Representation

    Department of Computer Vision, Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates. · School of Information Science and Technology, University of Science and Technology of China. · Shenzhen Campus of Sun Yat-Sen University.

  6. Boosting MLLM Spatial Reasoning with Geometrically Referenced 3D Scene Representations

    Mar 9, 2026Jiangye Yuan, Gowri Kumar, Baoyuan Wang3D Spatial ReasoningMultimodal Large Language Models

    Zillow Group

  7. Rheos: Modelling Continuous Motion Dynamics in Hierarchical 3D Scene Graphs

    Mar 9, 2026Iacopo Catalano, Francesco Verdoja, Javier Civera +23D Scene Representation

    University of Turku, Finland · School of Electrical Engineering, Aalto University, Finland · University of Zaragoza, Spain +2

  8. CylinderSplat: 3D Gaussian Splatting with Cylindrical Triplanes for Panoramic Novel View Synthesis

    Mar 6, 2026Qiwei Wang, Xianghui Ze, Jingyi Yu +1Tri-Plane RepresentationsNovel View Synthesis

    Shanghaitech University · Nanjing University of Science and Technology

  9. OWL: A Novel Approach to Machine Perception During Motion

    Mar 5, 2026Daniel Raviv, Juan D. Yepes3D Scene RepresentationMonocular 3D Reconstruction

    Electrical Engineering and Computer Science Department Florida Atlantic University Boca Raton, Florida, USA

  10. Beyond Pixel Histories: World Models with Persistent 3D State

    Mar 3, 2026Samuel Garcin, Thomas Walker, Steven McDonagh +5World ModelsInteractive World Models

    University of Edinburgh · Microsoft Research

  11. VIRGi: View-dependent Instant Recoloring of 3D Gaussians Splats

    Mar 3, 2026Alessio Mazzucchelli, Ivan Ojeda-Martin, Fernando Rivas-Manzaneque +33D Scene Editing3D Gaussian Splatting

    Arquimea Research Center, San Cristóbal de la Laguna, Santa Cruz de Tenerife, 38320 · Universidad Polit`ecnica de Catalunya, Doctoral Degree in Automatic Control, Robotics and Vision, Carrer de Jordi Girona, 31, Les Corts, Barcelona, 08034, Spain · Volinga AI, San Cristóbal de la Laguna, Santa Cruz de Tenerife, 38320 +4

  12. VGG-T3^3: Offline Feed-Forward 3D Reconstruction at Scale

    Feb 26, 2026Sven Elflein, Ruilong Li, Sérgio Agostinho +43D ReconstructionFeed-Forward 3D Reconstruction

    NVIDIA · Vector Institute · University of Toronto

  13. SeeThrough3D: Occlusion Aware 3D Control in Text-to-Image Generation

    Feb 26, 2026Vaibhav Agrawal, Rishubh Parihar, Pradhaan Bhat +2Controllable Image GenerationOcclusion Reasoning

    IIIT Hyderabad · IISc Bengaluru

  14. Efficient Encoder-Free Fourier-based 3D Large Multimodal Model

    Feb 26, 2026Guofeng Mei, Wei Lin, Luigi Riz +33D VLMsEfficient Multimodal Inference

    Fondazione Bruno Kessler, Italy · JKU Linz, Austria · CSIRO, Australia

  15. Space-Time Forecasting of Dynamic Scenes with Motion-aware Gaussian Grouping

    Feb 25, 2026Junmyeong Lee, Hoseung Choi, Minsu ChoSpatiotemporal Forecasting3D Gaussian Splatting

    Pohang University of Science and Technology (POSTECH) · RLWRLD

  16. Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoning

    Feb 24, 2026Haoyi Jiang, Liu Liu, Xinjie Wang +53D Spatial Reasoning3D VLMs

    School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China · Horizon Robotics, Beijing 100094, China · D-Robotics, Shenzhen 518055, China

  17. SceMoS: Scene-Aware 3D Human Motion Synthesis by Planning with Geometry-Grounded Tokens

    Feb 24, 2026Anindita Ghosh, Vladislav Golyanik, Taku Komura +3Human Motion GenerationText-to-Motion Generation

    DFKI · MPI for Informatics · Saarland Informatics Campus +1

  18. Large-scale Photorealistic Outdoor 3D Scene Reconstruction from UAV Imagery Using Gaussian Splatting Techniques

    Feb 23, 2026Christos Maikos, Georgios Angelidis, Georgios Th. PapadopoulosAerial 3D Reconstruction3D Reconstruction

    Department of Informatics and Telematics, Harokopio University of Athens, Athens, Greece · Archimedes, Athena Research Center, Athens, Greece

  19. Augmented Radiance Field: A General Framework for Enhanced Gaussian Splatting

    Feb 23, 2026Yixin Yang, Bojian Wu, Yang Zhou +13D Gaussian Splatting3D Scene Representation

    VCC, CSSE, Shenzhen University · Tencent Games

  20. SceneTok: A Compressed, Diffusable Token Space for 3D Scenes

    Feb 21, 2026Mohammad Asim, Christopher Wewer, Jan Eric Lenssen3D Scene Representation3D Scene Generation

    Max Planck Institute for Informatics, Saarland Informatics Campus

  21. Language and Geometry Grounded Sparse Voxel Representations for Holistic Scene Understanding

    Feb 17, 2026Guile Wu, David Huang, Bingbing Liu +13D Scene Understanding3D Scene Representation

    Huawei Noah’s Ark Lab · University of Toronto

  22. A2^2TG: Adaptive Anisotropic Textured Gaussians for Efficient 3D Scene Representation

    Jan 14, 2026Sheng-Chi Hsu, Ting-Yu Yen, Shih-Hsuan Hung +13D Gaussian SplattingNeural Rendering

    National Tsing Hua University

  23. PanoGrounder: Bridging 2D and 3D with Panoramic Scene Representations for VLM-based 3D Visual Grounding

    Dec 24, 2025Seongmin Jung, Seongho Choi, Gunwoo Jeon +23D Scene Representation3D Visual Grounding

    Seoul National University, South Korea · Robotics Lab, Hyundai Motor Company, South Korea · Pohang University of Science and Technology (POSTECH), South Korea

  24. Social 3D Scene Graphs: Modeling Human Actions and Relations for Interactive Service Robots

    Sep 29, 2025Ermanno Bartoli, Dennis Rotondi, Buwei He +3Human Activity Recognition3D SGG

    Faculty of Robotics Perception and Learning, KTH Royal Institute of Technology, Stockholm, Sweden · Socially Intelligent Robotics Lab at the Institute for Artificial Intelligence, University of Stuttgart, Germany · International Max Planck Research School for Intelligent Systems (IMPRS-IS)

  25. Effective Gaussian Management for High-fidelity Scene Reconstruction

    Sep 16, 2025Jiateng Liu, Hao Gao, Jiu-Cheng Xie +53D Gaussian Splatting3D Reconstruction

    School of Automation, Nanjing University of Posts and Telecommunications, Nanjing, 210023, China · Department of Computer and Information Science, University of Macau, Taipa, Macau · school of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, 210023, China +2

  26. GaussianArt: Unified Modeling of Geometry and Motion for Articulated Objects

    Aug 20, 2025Licheng Shen, Saining Zhang, Honghan Li +4Articulated Object Reconstruction3D Gaussian Splatting

    BAAI · AIR, THU · NTU +2

  27. VLEM: Real-Time 3D Vision-Language Embedding Mapping

    Aug 8, 2025Christian Rauch, Björn Ellensohn, Linus Nwankwo +2Open-Vocabulary 3D Segmentation3D Scene Representation

    Technical University of Leoben, Franz Josef-Straße 18, 8700 Leoben, Austria

  28. DINO-SLAM: DINO-informed RGB-D SLAM for Neural Implicit and Explicit Representations

    Jul 25, 2025Ziren Gong, Xiaohan Li, Fabio Tosi +4Simultaneous Localization and MappingNeural Representation Geometry

    University of Bologna, Italy · Faculty of Dentistry, The University of Hong Kong, China · Rawmantic AI, China +1

  29. 3D Software Synthesis Driven by Constraint-Expressive Intermediate Representation

    Jul 24, 2025Shuqing Li, Anson Y. Lam, Yun Peng +2Program Synthesis3D Scene Generation

    The Chinese University of Hong Kong Hong Kong, China · Renmin University of China Beijing, China

  30. ReSpace: Text-Driven Autoregressive 3D Indoor Scene Synthesis and Editing

    Jun 3, 2025Martin JJ. Bucher, Iro Armeni3D Scene Editing3D Scene Representation

    Stanford University