Indoor Scene Reconstruction

Ask about this topic

Overview

Indoor scene reconstruction studies how to turn images, video, depth, and sensor scans into coherent 3D models of rooms, objects, and their spatial relationships. Methods range from SLAM, neural implicit surfaces, and 3D Gaussian Splatting to structured scene programs and generative models that complete missing geometry; multi-view panoramas and semantic cues help recover larger spaces. Accurate, editable reconstructions support digital twins, architectural analysis, and embodied robots that need to navigate or manipulate objects. A central challenge is balancing plausible completion with fidelity to observed evidence, especially when views are sparse, rooms are cluttered, or scale and viewpoint coverage are uncertain.

Latest papers

CardsList

40 papers10 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

  1. RoomRecon: High-Quality Textured Room Layout Reconstruction on Mobile Devices

    Apr 21, 2026Seok Joon Kim, Dinh Duc Cao, Federica Spinola +23D ReconstructionIndoor Scene Reconstruction

    MAXST Co., Ltd. · Independent Researcher

  2. Incremental Semantics-Aided Meshing from LiDAR-Inertial Odometry and RGB Direct Label Transfer

    Apr 10, 2026Muhammad Affan, Ville Lehtola, George Vosselman3D Reconstruction3D Mesh Reconstruction

    Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, 7522 NB Enschede, Netherlands

  3. FunRec: Reconstructing Functional 3D Scenes from Egocentric Interaction Videos

    Apr 7, 2026Alexandros Delitzas, Chenyangguang Zhang, Alexey Gavryushin +83D ReconstructionHuman-Scene Interaction Reconstruction

    ETH Zurich · Max Planck Institute for Informatics · Stanford University +2

  4. SGS-Intrinsic: Semantic-Invariant Gaussian Splatting for Sparse-View Indoor Inverse Rendering

    Mar 29, 2026Jiahao Niu, Rongjia Zheng, Wenju Xu +2Inverse RenderingIndoor Scene Reconstruction

    Sun Yat-sen University, China · Amazon, USA · Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China

  5. KitchenTwin: Semantically and Geometrically Grounded 3D Kitchen Digital Twins

    Mar 25, 2026Quanyun Wu, Kyle Gao, Daniel Long +3Digital Twins3D Scene Representation

    University of Waterloo, Waterloo, ON, Canada

  6. Training-Free Instance-Aware 3D Scene Reconstruction and Diffusion-Based View Synthesis from Sparse Images

    Mar 22, 2026Jiatong Xia, Lingqiao LiuIndoor Scene ReconstructionSparse-View 3D Reconstruction

    The University of Adelaide, Australia

  7. PixARMesh: Autoregressive Mesh-Native Single-View Scene Reconstruction

    Mar 6, 2026Xiang Zhang, Sohyun Yoo, Hongrui Wu +3Autoregressive 3D Scene Generation3D Mesh Reconstruction

    UC San Diego · Lambda, Inc.

  8. Leveraging Geometric Prior Uncertainty and Complementary Constraints for High-Fidelity Neural Indoor Surface Reconstruction

    Feb 27, 2026Qiyu Feng, Jiwei Shan, Shing Shin Cheng +1UQ for 3D Reconstruction3D Reconstruction

    Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, China. · Department of Mechanical and Automation Engineering and T Stone Robotics Institute, The Chinese University of Hong Kong, Hong Kong.

  9. Have We Mastered Scale in Deep Monocular Visual SLAM? The ScaleMaster Dataset and Benchmark

    Feb 20, 2026Hyoseok Ju, Bokeon Suh, Giseop KimVisual SLAMIndoor Scene Reconstruction

    Department of Robotics and Mechatronics Engineering, DGIST, Daegu, Republic of Korea

  10. PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-Forward Planar Splatting

    Oct 21, 2025Changkun Liu, Bin Tan, Zeran Ke +63D ReconstructionIndoor Scene Reconstruction

    The Hong Kong University of Science and Technology · Ant Group · Wuhan University +2