Monocular 3D Reconstruction

Overview

Monocular 3D reconstruction turns images or video from one camera into estimates of shape, depth, camera motion, and sometimes changing objects or people. Methods range from structure-from-motion and SLAM to learned depth and point-map models, neural radiance fields, and 3D Gaussian splatting, often strengthened with geometric, semantic, or physical priors. Current work increasingly uses pretrained vision models and feed-forward systems for faster reconstruction, while specialized methods address people, hands, interactions, medical scenes, and long videos. A central challenge remains that one view does not uniquely determine 3D scale or hidden structure, especially when the camera and scene both move; accuracy, temporal consistency, generalization, and runtime can trade off.

Latest papers

CardsList

119 papers8 papers in the last four weeks, up 33% on the four weeks before. 0.1% of all new papers.

  1. PhyVGGT: Feed-Forward Articulated Object Reconstruction from Monocular Videos

    Nov 17, 2026Qi Shao, Zhihao Cao, Shuhao Zhai +4Articulated Object ReconstructionMonocular 3D Reconstruction

  2. MetricTrail: Revisiting the Power of Metric Depth and Local Optimization for Long-Sequence Streaming 3D Reconstruction

    Nov 5, 2026Jingnan Gao, Jiahui Huang, Sven Elflein +8Streaming 3D ReconstructionMonocular 3D Reconstruction

  3. EgoMo3R: Joint Egocentric Motion and Scene Reconstruction

    Nov 1, 2026Chaitanya Patel, Yusuke Kato, Rin Takahira +33D ReconstructionEgocentric Video Understanding

  4. Volley3D: Unified 3D Full-Sequence Reconstruction from Monocular Broadcasts

    Oct 28, 2026Noâm Boussouf, Adrien Maglo, Mohamed Chaouch +1Monocular 3D ReconstructionSports Video Analysis

  5. LabWorld: Learning Interactive 4D Worlds for Scientific Experimentation

    Oct 27, 2026Suozhi Huang, Kelsey Fu, Binxu Li +124D ReconstructionIndoor Scene Reconstruction

  6. SG^2SLAM: Spatial Geometry-Informed 3D Gaussian Splatting SLAM for Monocular Outdoor Navigation

    Oct 26, 2026Ziang Guo, Didar Seyidov, Yixiao Zhou +53DGS SLAMVisual SLAM

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

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

  8. EgoXperience: Learning World-Grounded Egocentric Representations from Human Experience

    Oct 19, 2026Xinhao Ji, Hui En Pang, Hao Li +123D ReconstructionHand-Object Interaction Reconstruction

  9. HORIA: 4D Human and Object Reconstruction from a Monocular Video with Interaction-Aware Re-Rendering

    Oct 19, 2026Hyeongjin Nam, Taeryung Lee, Daniel Sungho Jung +1Human-Scene Interaction Reconstruction4D Reconstruction

  10. ORMA: Optimization-based Monocular 4D Reconstruction of Articulated Animals

    Sep 29, 2026Xuyi Hu, Francesco Palandra, Shangzhe Wu +3Articulated Object Reconstruction4D Reconstruction

  11. DynamicHOI: Coupled Dynamics for Physics-aware HOI Reconstruction

    Sep 29, 2026Wenliang Guo, Zhanbo Huang, Yu Kong3D ReconstructionMonocular 3D Reconstruction

  12. AgentSTAR: Agentic Shape Tracking and Reconstruction from Monocular Videos

    Sep 21, 2026Kirill Mazur, Nikita Karaev, Matthew Chang +2Articulated Object ReconstructionVisual Object Tracking

  13. GRF-Recon: Global Ray-Field Optimization for Long-Sequence Feed-forward Reconstruction

    Sep 17, 2026Enpeng Li, Yunzhou Zhang, Zhiyao Zhang +43D ReconstructionMonocular 3D Reconstruction

  14. Visual-SLAM for the detection of hidden tomatoes in greenhouses by Hierarchical Localization and GLOMAP for robotized harvesting

    Sep 10, 2026Fernando Cañadas-Aránega, José C. Moreno, José L. Blanco-Claraco +1Monocular 3D ReconstructionVisual SLAM

  15. OmniPoint: Universal Monocular Metric Pointcloud from Any Camera

    Sep 8, 2026Botao Ye, Marc Pollefeys, Ming-Hsuan Yang +1Panoramic 3D Reconstruction3D Reconstruction

  16. NeoWorld-Pro: Programming Interactive Scenes from Monocular Images for Embodied Simulation

    Aug 25, 2026Yumeng He, Eachen Soong, Xiaotian Yang +53D Scene GenerationMonocular 3D Reconstruction

  17. Depth Anything V4: Dynamic 4D Scene Reconstruction via Riemannian Flow Matching on 4D Gaussian Splatting

    Aug 18, 2026Jiaming Fan, Jian Lu, Jinling Jia +14D ReconstructionDynamic Scene Reconstruction

  18. RealDenseFace: Real-time Monocular 3D Face Reconstruction from Dense UV-space Priors

    Aug 10, 2026Linzhou Li, Tianjia Shao, Kun ZhouStreaming 3D Reconstruction3D Morphable Models

  19. AdaAnchor4D: Anchor-Conditioned Spatiotemporal Feature Aggregation for Monocular UAV 4D Reconstruction

    Jul 30, 2026Peiyi Xu, Junpeng Zhang, Guanbin Li +64D ReconstructionDynamic Gaussian Splatting

  20. MonoVoc: Decoupling Geometry and Semantics for Lightweight Monocular Open-Vocabulary 3D Gaussians

    Jul 30, 2026Pouya Ardekhani, Zahra Dehghanian, Morteza Abolghasemi +13D Gaussian Splatting3D Semantic Mapping

  21. SM4RT: Learning Structured Motion Geometry for 4D Reconstruction

    Jul 24, 2026Shing Ho J. Lin, Wenzhao Zheng, Dong Zhuo +33D ViTs4D Reconstruction

  22. Metric Surface Reconstruction of Neurosurgical Scenes from Monocular Operating Microscope Images and Microscope Pose

    Jul 24, 2026Thomas Bucher, Didier Neuenschwander, Thomas Petutschnigg +4Metric Depth Estimation3D Reconstruction

  23. Crowd4D: Scene-Aware Monocular 4D Crowd Reconstruction

    Jul 21, 2026Hongbo Kang, Tianyi Zhou, Qingyang Yang +4Monocular 3D ReconstructionDynamic Scene Reconstruction

  24. FlexiAvatar: Unified 3D Gaussian Human Avatars Under Arbitrary Body Visibility

    Jul 21, 2026Yihalem Yimolal Tiruneh, Muhammad Salman Ali, Uyoung Jeong +53D Gaussian Splatting3D Reconstruction

  25. MoGe-3: Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement

    Jul 20, 2026Lingyu Kong, Ruicheng Li, Ruicheng Wang +4Monocular 3D Reconstruction3D Scene Representation

  26. VIDAR: Visual-Inertial Dense Alignment and Reconstruction via a Geometric Foundation Model

    Jul 19, 2026Diyari Mohammed Salih, Lingxiang Hu, Naima AitOufroukh-Mammar +1Monocular 3D Reconstruction