Overview

3D scene understanding studies how to recover the geometry, objects, relationships, and often motion of environments from images, depth, and LiDAR. Common approaches include point-cloud and voxel networks, occupancy prediction, Gaussian splatting, and 3D scene graphs, increasingly combined with vision-language models for grounding and reasoning. These representations support tasks such as robot navigation and manipulation, autonomous driving, scene reconstruction, and open-vocabulary object retrieval. A central challenge is making systems both spatially reliable and efficient in large, changing scenes, while benchmarks continue to expose gaps in metric reasoning, cross-view consistency, and generalization.

Latest papers

CardsList

308 papers22 papers in the last four weeks, down 37% on the four weeks before. 0.2% of all new papers.

  1. A forensic evaluation framework for egocentric foundation models: an EFM3D case study for crime scene reconstruction

    Nov 9, 2026Davidson Chisom Onwubiko, Shahana Bano, Carlos Francisco Moreno-García3D Foundation ModelsIndoor Scene Reconstruction

  2. From Geometry to Function: A Multi-Task LiDAR Benchmark Dataset for Semantic and Functional Parsing of Urban Facades

    Nov 5, 2026Abdiaziz Muse, Tooba Javed, Tao Pu +23D Scene Understanding3D Semantic Segmentation

  3. Spatial-UMI-Dream: Scaling World Action Models with Metric Geometry for UMI Manipulation

    Nov 4, 2026Weiduo Yuan, Ze Yuan, Sihan Liu +4World Models for RoboticsWorld Action Models

  4. BhopalMLS: A LiDAR Dataset for Semantic Scene Understanding in Heterogeneous Urban Environments

    Nov 3, 2026Pyare Lal Chauhan, Vaibhav Kumar, Bharat Lohani3D Scene Understanding3D Point Cloud Segmentation

  5. SparseGraph-I2P: Consistency-Guided Hypothesis Selection for Efficient Image-to-Point-Cloud Registration

    Nov 3, 2026Ziyang Yu, Xiang Li, Qiong Chang +12D-3D Image RegistrationPoint Cloud Registration

  6. CoLa3D: Composable Latent 3D Decomposition

    Nov 2, 2026Xudong Cai, Yongcai Wang, Deying Li +13D Scene UnderstandingObject-Centric 3D Reconstruction

  7. Lie Routing Vision Language Models for View-Robust 3D Understanding

    Nov 1, 2026Jingjun Yi, Chen Hu, Qi Bi +73D VLMs3D Scene Understanding

  8. VLSplat: Vision-Language Guided Object-Centric 3D Gaussian Splatting via Scene Graph

    Nov 1, 2026Yuntae Jeon, Younho Jeon, Sujin Jin +2Language-Embedded 3DGS3DGS Segmentation

  9. MMCoT3^3: Empowering 3D Scene Understanding with 3D-Text Interleaved Multi-Modal Chain-of-Thought Reasoning

    Nov 1, 2026Yongqi Shan, Yifan Wang, Yunzhi Zhuge +23D Scene Understanding3D VLMs

  10. LucidLyra: Feed-Forward Generative 3D Scene Reconstruction and Joint Understanding via Multi-Task Distillation

    Oct 29, 2026Oliver Hahn, Rodrigo Marcuzzi, Sangeetha Grama Srinivasan +73D Scene Understanding3D Scene Generation

  11. 3D-SceneQ: Empowering 3D LLM With Query-Guided Adaptive Pruning and Multi-Modal Feature Enhancement

    Oct 27, 2026Yongqi Shan, Lu Zhang, Jiazuo Yu +23D Scene Understanding3D VLMs

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

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

  13. Point-Level Refinable Semantic Mapping for Spatial Understanding

    Oct 22, 2026Taimeng Fu, Yi Du, Zitong Zhan +43D Semantic MappingSemantic Mapping

  14. OMAR: Open-World Multi-Attribute Reasoning for Scene-Conditioned Shelf Organization

    Oct 21, 2026Benedikt Kreis, Rohit Menon, Benno Wingender +3Robotic ManipulationMultimodal Spatial Reasoning

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

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

  16. PanoGraphGS: Unifying Panoptic Segmentation and Hierarchical 3D Scene Graphs with Gaussian Splatting

    Oct 20, 2026Jinghan Gao, Siyu Wang, Dongyu Feng +23D SGG3D Scene Understanding

  17. Where Do the Gaussians Go? Foreground Attraction for Camera-Based Weakly Supervised 3D Occupancy

    Oct 19, 2026Jeagon Song, Jhonghyun An3D Occupancy Prediction3D Scene Understanding

  18. From Views to Worlds: Active Exploration over 3D Worlds for Vision-Language Models

    Oct 17, 2026Qijian Tian, Jiayu Ying, Ke Fan +2Visual Spatial Reasoning3D Scene Understanding

  19. O-SCD++: Replay-Free Online Scene Change Detection via Recursive Evidence Fusion

    Oct 17, 2026Chamuditha Jayanga Galappaththige, Jason Lai, Lloyd Windrim +43D Scene Change Detection3D Scene Understanding

  20. Grounding Generative Verification in 3D Content

    Oct 15, 2026Shuanglin Li, Jiaying Lin, Shuquan Ye3D Scene Understanding

  21. FALCON: FPGA-Accelerated Latency-Certifiable Occupancy Networks for Camera-Based Autonomous Driving

    Oct 15, 2026Haohua Que, Mingkai Liu, Handong YaoAutonomous Driving PerceptionFPGA-Based Neural Network Acceleration

  22. DeSpatial: The devil of Agentic Spatial Reasoning Lies in 3D Itself

    Oct 14, 2026Yifei Liu, Xiaolong Zhou, Ziyang Gong +83D Spatial Reasoning3D Scene Understanding