Overview

Camera pose estimation determines where a camera is and how it is oriented, enabling localization, 3D reconstruction, visual odometry, and robotic navigation. Classical approaches use point, line, or region correspondences with PnP and relative-pose solvers, then refine poses through bundle adjustment or pose-graph optimization; visual odometry and SLAM extend these methods across sequences. Learned approaches range from pose-regression networks to feed-forward 3D models, often combining geometric constraints, depth priors, or camera data from inertial, event, thermal, and other sensors. Work spans settings such as indoor and outdoor localization, driving, medical imaging, and wide-angle or dynamic scenes, while balancing accuracy and efficiency against drift, ambiguous geometry, calibration errors, and poor generalization to unfamiliar conditions.

Latest papers

CardsList

271 papers36 papers in the last four weeks, up 50% on the four weeks before. 0.3% of all new papers.

  1. What Do Learned 3D Models Add to Localization from Posed References?

    Nov 18, 2026Jaehyun Kim, Wonseok Kang, Jeongmin Lee +1Camera Pose EstimationRobot Localization

  2. π4π^4: A Foundation Model for 4D Scene Geometry and Motion

    Nov 17, 2026Yifan Wang, Weiguang Zhao, Ni Yang +44D Scene UnderstandingMulti-View 3D Reconstruction

  3. Kolibri: Color Finds the Place, Refinement Sets the Pose for RGB-D Localization in Colored Point Clouds

    Nov 17, 2026Leonel Aguilar, Bartu Tuncay, Christoph HoelscherRobot LocalizationCamera Pose Estimation

  4. Every Camera Grows Up: Camera-Height Regression in Interactive Video World Models

    Nov 16, 2026Sheng Lu, Guangpin Tao, Tong Lu +1Interactive World ModelsWorld Model Evaluation

  5. Déjà-Events: Multi-view 3D Geometry with Event Cameras via Sparsity-Aware Adaptive Gating

    Nov 16, 2026Arda Cinar Demirtas, Pablo Varela Bernal, Marc Pollefeys +1Multi-View Depth EstimationEvent-Based Vision

  6. Correspondence-Free Camera Pose Estimation by Matching Moments

    Nov 16, 2026Subhransu S. Bhattacharjee, Dylan Campbell, Rahul ShomeCamera Pose EstimationPnP Pose Estimation

  7. Deep Bundle Adjustment

    Nov 13, 2026Pak Hong Chui, Hector Andrade-Loarca, Daniel CremersMulti-View 3D ReconstructionStructure from Motion

  8. Kosmo-GFM: A Production-Ready Geometry Foundation Model

    Nov 12, 2026Sheng Tang, Shengzhe Wei, Tiancheng Chen +293D ReconstructionMulti-View Geometry

  9. ReFineR: Single image to dense point cloud registration at pixel level with point splatting

    Nov 12, 2026Ugo Insalaco, Jean-Emmanuel Deschaud, Pierre DellenbachPoint Cloud RegistrationCross-Modal Image Registration

  10. UGG: Unified Generative Geometry Model

    Nov 10, 2026Amani Kiruga, Zhiyi Li, Ruojin Cai +44D Scene UnderstandingCamera Pose Estimation

  11. Towards Rotation-Only Imaging Geometry: Multi-View Pose Estimation

    Nov 9, 2026Xinrui Li, Qi Cai, Yuanxin WuCamera Pose EstimationStructure from Motion

  12. DAC-MACE: Context-Conditioned Expert Routing for Compact Scene Coordinate Regression in Camera Relocalization

    Nov 6, 2026Dingying Fan, Mingkai Liu, Haohua Que +5Scene Coordinate RegressionCamera Pose Estimation

  13. Direct Regression and Geometric Recovery for Event-based Spacecraft Pose Estimation

    Nov 6, 2026Pruthvi Nandan Janga, Kashyap Hegde Kota, Bharatesh ChakravarthiSpacecraft Pose EstimationCamera Pose Estimation

  14. XM4D: 4D Reconstruction through Certifiable Geometric Optimization

    Nov 5, 2026Haoyu Han, Jack Benarroch Jedlicki, Jiahui Lei +14D ReconstructionDynamic Scene Reconstruction

  15. 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

  16. DUNEDepth: Bronchoscopic Depth and Pose Estimation via Hybrid Adaptation of a 3D-Vision Foundation Model

    Nov 2, 2026Qi Chang, Austin Kao, Ange Lou +1Depth EstimationCamera Pose Estimation

  17. Ray-SCR: Generalizing Scene Coordinate Regression Across Camera Models

    Nov 2, 2026Jaemin Cho, Oleksii Nasypanyi, Francois RameauScene Coordinate RegressionCamera Pose Estimation

  18. AnchorHEC: Targetless Hand-Eye Calibration of Wrist and Fixed Cameras

    Nov 2, 2026Guebin Hwang, Taeyeop Lee, Yeonseo Lee +2Hand-Eye CalibrationCamera Pose Estimation

  19. Rethinking Asymmetry in Self-Supervised 3D Geometry Learning

    Oct 30, 2026Gyeongjin Kang, Freeman Cheng, Botao Ye +33D Representation LearningMulti-View 3D Reconstruction

  20. PGGT-Loc: Primitive-Grounded Geometry Transformer for Feed-Forward Camera Localization

    Oct 30, 2026Hanqiao Ye, Yuzhou Liu, Mengqi Rong +3Camera Pose EstimationMap-Based Localization

  21. Queryable Gaussian View Index: Text Retrieval and Selective Camera Localization

    Oct 30, 2026Tianyu Xiong, Rui Li, Jiaqi YangCamera Pose EstimationVision-Language Retrieval

  22. LingGS: Decoupling Feed-Forward Geometry Prediction from Camera Tracking for High-Fidelity Gaussian SLAM

    Oct 27, 2026Da Li, Yihan Zang, Ivan Viola +23DGS SLAMStreaming 3D Reconstruction

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

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

  24. Any3R: Feedforward 3D Reconstruction from Any Camera Type

    Oct 26, 2026Jingong Chen, Qingwen Zhang, Youming Deng +53D ReconstructionMulti-View 3D Reconstruction