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

252 papers16 papers in the last four weeks, down 57% on the four weeks before. 0.1% of all new papers.

  1. Split-and-scale Latent 3D Representations

    Nov 12, 2026Dorian Chan, Muhammed Kocabas, Xiaoming Zhao +23D Scene Representation3D Representation Learning

  2. Spaghetti Splatting: Differentiating Curvilinear Dirac Masses via Convolution

    Nov 9, 2026George Shramko, Shrisudhan Govindarajan, Rudy Lam +43D Scene RepresentationDifferentiable Rendering

  3. Video2Asset: Online Construction of Persistent 3D Street-Scene Assets

    Nov 6, 2026Zihan Zheng, Chunlei Cai, Zhenlong Wu +43D Reconstruction3D Scene Representation

  4. Bri3D: Bridging the Object-Scene Gap in Single-Image 3D Generation via Scene-Anchor

    Nov 5, 2026Hongye Hou, Shuai Zhang, Hongjie Li +4Image-to-3D Scene Generation3D Scene Layout Generation

  5. Gaussians Can Subtract: Neural Dissolve Fields for Hybrid Scene Rendering

    Nov 4, 2026Yiyan Wang, Haohan Liu, Tetsuo Shibuya3D Scene RepresentationNeural Rendering

  6. Hybrid Particle-Voxel Dynamics for Multimodal 3D World Simulation

    Nov 3, 2026Jimmy Wang, Yifan Chou, Kaifeng Zhang +5World Models for Robotics3D Scene Prediction

  7. AbacusGS: Gaussian Splatting without Per-Splat Sorting

    Nov 1, 2026Jiacheng Ding, Yanliang Qi, Cong Guo +13D Gaussian Splatting3DGS Acceleration

  8. VoxLution: Evolving Voxels for High-Fidelity 3D Scene Generation

    Oct 30, 2026Daoyi Gao, Xinyi Zhang, Alexey Bokhovkin +23D Scene GenerationIndoor Scene Generation

  9. RelateGS: Reliable Semantic and Relational Evidence for 3D Scene Understanding with Gaussian Splatting

    Oct 24, 2026Seongjun Choi, Sangyoun Lee3D Scene Understanding3D Visual Grounding

  10. OmniRay: Camera-Agnostic Monocular 3D Reconstruction with Composite Ray Fields

    Oct 22, 2026Namitha Guruprasad, Abhay Yadav, Cheng Peng +23D ReconstructionMonocular 3D Reconstruction

  11. CoGaussian: Open-Vocabulary Gaussian-based Collaborative 3D Scene Understanding

    Oct 20, 2026Om Shivam Verma, Shaya Farahmand, Lingjun Zhao +13D Scene Understanding3D Occupancy Prediction

  12. OV-Foam: How 3D Representations Shape Semantic Feature Lifting

    Oct 20, 2026Yousef Rajeh, Alejandra Esparza Pelcastre, Ivan Viola +1Open-Vocabulary 3D Segmentation3D Scene Representation

  13. SwitchSplat: Learning Discrete Object States from Casually Captured Scenes

    Oct 17, 2026Yizheng Xie, Yalda Foroutan, George Shramko +33D Scene Representation3D Gaussian Splatting

  14. Persistent Planar Memory for Video World Models

    Oct 16, 2026Yuze He, Bin Tan, Zelin Gao +4Video World ModelsMemory-Augmented Video Generation

  15. GeoState: Learning View-Decoupled Geometry States for 3D World Modeling

    Oct 15, 2026Hongchang Liu, Jian Liu, Yujuan Ding +5World Model Learning3D Scene Prediction

  16. GRASE: Geometry-native Real-to-sim Agentic Scene Modeling from Video

    Oct 15, 2026Zhaorui Lin, Haohan Liu, Zhen Chen +1Real-to-Sim Transfer3D Scene Representation

  17. GLoD-LVSM: Learning Geometry-Grounded Continuous-LoD Scene Representations for Large View Synthesis Models

    Oct 14, 2026Weikai Lin, Nicholas Milef, Carl S Marshall +33D Scene RepresentationNovel View Synthesis

  18. SceneAE: Scene Generation and Reconstruction in Queryable 3D-Anchored Latent Space

    Oct 14, 2026Shuofeng Sun, Wenzhao Zheng, Yunpeng Zhang +33D Scene Generation3D Scene Representation

  19. CoTL: Compact Token Learning for 3D Scene Representation

    Oct 13, 2026Han Liang, Sibo Wu, Anpei Chen +13D Scene RepresentationMulti-View 3D Reconstruction

  20. CityCode: Building Agent-Operable 3D Cities from Sparse Aerial Observations

    Oct 13, 2026Jiahui Sun, Ran Bi, Yifei Liu +8Aerial 3D Reconstruction3D Scene Representation

  21. EgoAlign: Situated 3D Understanding without Situation Descriptions

    Oct 12, 2026Yiyang Li, Tianyi Ma, Zehong Wang +13D Visual Question Answering3D VLMs

  22. Make It Flow: Animating Water in 3D Gaussian Splatting Scenes

    Oct 9, 2026Kjell Keune, Florian Hahlbohm, Jannis Möller +33D Gaussian Splatting3D Scene Representation

  23. UNITAS: A 3D-Native World Action Model for Embodied Manipulation

    Oct 8, 2026Ruixiang Wang, Yongyi Su, Wenlve Zhou +14World Action ModelsEmbodied World Models

  24. PAM-ToD: Plug-and-Play Appearance Modeling for Cross-Time-of-Day 3D Gaussian Splatting

    Oct 8, 2026Kota Shimomura, Sungho Moon, Tsubasa Hirakawa +33D Scene Relighting3D Gaussian Splatting

  25. NeRFifyMesh: Optimizing Neural Radiance Fields from Textured Meshes for Robotics Scene Building

    Oct 7, 2026Nillan Nimal, Mahboubeh Asadi, Sajad Saeedi3D Scene RepresentationNeural Radiance Fields

  26. ActiveLang: Active Open-Vocabulary 3D Mapping with Semantic-Uncertainty-Guided Exploration

    Oct 7, 2026Liyan Chen, Hairong Yin, Huangying Zhan +33D Semantic Mapping3D Mapping