Camera Pose Estimation

Follow this topic Ask about this topic

Momentum

14 papers in the last four weeks, up 27% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 138

All topics

Global Structure-from-Motion Meets Feedforward Reconstruction
May 25, 2026Linfei Pan, Johannes Schönberger, Marc PollefeysMulti-View 3D Reconstruction Camera Pose Estimation
ETH Zurich · Meta Reality Labs · ETH Zurich, Microsoft
HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction
May 22, 2026Chong Cheng, Peilin Tao, Nanjie Yao +93D ViTs Streaming 3D Reconstruction
HKUST(GZ) · Horizon Robotics · CASIA +2
Cambrian-P: Pose-Grounded Video Understanding
May 21, 2026Jihan Yang, Zifan Zhao, Xichen Pan +5Vision-Language Models Camera Pose Estimation
New York University · UC Berkeley · Meta FAIR
Landscape-Awareness for Geometric View Diffusion Model
May 19, 2026Yan-Ting Chen, Hao-Wei Chen, Tsu-Ching Hsiao +1Diffusion Model Guidance Camera Pose Estimation
Elsa Lab, National Taiwan University
EpiDiffVO: Geometry-Aware Epipolar Diffusion for Robust Visual Odometry
May 19, 2026Prateeth RaoMulti-View Geometry Relative Pose Estimation
International Institute of Information Technology Bangalore, Bengaluru, India
NeRF-based Spacecraft Reconstruction from Monocular Imagery Under Illumination Variability and Pose Uncertainty
May 18, 2026Antoine Legrand, Renaud Detry, Christophe De VleeschouwerDistribution Shift 3D Reconstruction
Aerospacelab, Mont-Saint-Guibert, 1435, Belgium · ICTEAM, UCLouvain, Louvain-la-Neuve, 1348, Belgium
UAVFF3D: A Geometry-Aware Benchmark for Feed-Forward UAV 3D Reconstruction
May 18, 2026Xiang Yang, Yongli Wang, HaiFeng Li +1Domain Adaptation 3D Reconstruction
aSchool of Geosciences and Info-Physics, Central South University, Changsha, China
Efficient Sparse-to-Dense Visual Localization via Compact Gaussian Scene Representation and Accelerated Dense Pose Estimation
May 18, 2026Zizhuo Li, Songchu Deng, Linfeng Tang +13D Gaussian Splatting Camera Pose Estimation
Electronic Information School, Wuhan University, Wuhan 430072, China · School of Robotics, Wuhan University, Wuhan 430072, China
LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos
May 17, 2026Chenyi Xu, Yihao Wu, Liqi Yan +43D Point Tracking 4D Reconstruction
Hangzhou Dianzi University
SCARED-C: Corrected Camera Poses for Endoscopic Depth Estimation
May 15, 2026John J. Han, Adam Schmidt, Max Allan +2Endoscopy Depth Estimation
Vanderbilt University Nashville, TN, USA · Intuitive Surgical, Inc. Sunnyvale, CA, USA
WildPose: A Unified Framework for Robust Pose Estimation in the Wild
May 12, 2026Jianhao Zheng, Liyuan Zhu, Zihan Zhu +1Camera Pose Estimation Visual SLAM
1Stanford University · 2ETH Zürich
PoseCompass: Intelligent Synthetic Pose Selection for Visual Localization
May 12, 2026Yanan Zhou, Zhaoyan Qian, Yanli Li +3Visual Place Recognition Camera Pose Estimation
The University of Sydney, Australia · University of St Andrews, United Kingdom
Seeing Across Skies and Streets: Feedforward 3D Reconstruction from Satellite, Drone, and Ground Images
May 8, 2026Qiwei Wang, Zhongyao Tuo, Xianghui Ze +1Relative Pose Estimation Cross-View Geo-Localization
ShanghaiTech University Shanghai, China · Nanjing University of Science and Technology Nanjing, China
Disambiguating 2D-3D Correspondences in Gaussian Splatting-based Feature Fields for Visual Localization
May 8, 2026Miso Lee, Sangeek Hyun, Yerim Jeon +13D Gaussian Splatting Visual Place Recognition
Sungkyunkwan University
TriP: A Triangle Puzzle Approach to Robust Translation Averaging
May 8, 2026Zhekai Fan, Wanze Li, Jinxin Wang +1Multi-View Geometry Camera Pose Estimation
UC Davis · University of Chicago
TriDE: Triangle-Consistent Translation Directions for Global Camera Pose Estimation
May 7, 2026Francisco Chen, Yiran Wang, Yunpeng ShiMulti-View Geometry Relative Pose Estimation
Department of Mathematics University of California, Davis
Solving Minimal Problems Without Matrix Inversion Using FFT-Based Interpolation
May 7, 2026Haidong Wu, Snehal Bhayani, Janne HeikkiläMulti-View Geometry Camera Pose Estimation
Center for Machine Vision and Signal Analysis University of Oulu, Oulu, Finland
egenioussBench: A New Dataset for Geospatial Visual Localisation
May 6, 2026Phillipp Fanta-Jende, Francesco Vultaggio, Alexander Kern +2Cross-View Geo-Localization Visual Place Recognition
Unit Assistive and Autonomous Systems, Center for Vision, Automation and Control, AIT Austrian Institute of Technology, Vienna, Austria · Institute of Geodesy and Photogrammetry, Technische Universität Braunschweig, Brunswick, Germany · Institute of Flight Guidance, Technische Universität Braunschweig, Brunswick, Germany
Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimation
May 5, 2026Siyou Lin, Zhou Xue, Hongwen Zhang +43D Reconstruction Multi-View 3D Reconstruction
Tsinghua University · Beijing Normal University · ByteDance
GeoBlur: Epipolar Geometry Estimation from a Single Motion-Blurred Image
May 2, 2026Bao-Long Tran, Cuong Le, Fredrik Viksten +1Multi-View Geometry Camera Pose Estimation
Computer Vision Laboratory, Linköping University, Sweden
Depth-Guided Privacy-Preserving Visual Localization Using 3D Sphere Clouds
May 1, 2026Heejoon Moon, Jongwoo Lee, Jeonggon Kim +1Camera Pose Estimation 3D Scene Representation
Department of Artificial Intelligence Hanyang Univeristy Seoul, Republic of Korea · Department of Electronic Engineering Hanyang Univeristy Seoul, Republic of Korea
Adaptive Geodesic Conformal Prediction for Egocentric Camera Pose Estimation
Apr 30, 2026Aishani Pathak, Hasti SeifiUncertainty Quantification Camera Pose Estimation
Arizona State University
LA-Pose: Latent Action Pretraining Meets Pose Estimation
Apr 30, 2026Zhengqing Wang, Saurabh Nair, Prajwal Chidananda +4Self-Supervised Pre-Training Camera Pose Estimation
1Wayve · 2Simon Fraser University
A Pose-only Geometric Constraint for Multi-Camera Pose Adjustment
Apr 26, 2026Shunkun Liang, Banglei Guan, Bin Li +2Multi-View Geometry Bundle Adjustment
College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410000, China
Preserve, Then Resolve: Many-to-Many Association and Robust Estimation with General-Purpose Visual Features
Apr 26, 2026Haodong Jiang, Mingzhe Li, Junfeng WuRelative Pose Estimation Image Matching
School of Data Science, CUHK (SZ)
SS3D: End2End Self-Supervised 3D from Web Videos
Apr 24, 2026Marwane Hariat, Gianni Franchi, David Filliat +1Self-Supervised Pre-Training Depth Estimation
U2IS, ENSTA – Institut Polytechnique de Paris, Palaiseau, France · Pôle Recherche, Agence Ministérielle pour l’IA de Défense, Palaiseau, France
Non-Minimal Sampling and Consensus for Prohibitively Large Datasets
Apr 24, 2026Seong Hun Lee, Patrick Vandewalle, Javier CiveraCamera Pose Estimation Point Cloud Registration
I3A, University of Zaragoza, 50018 Zaragoza, Spain · EAVISE, KU Leuven, 2860 Sint-Katelijne-Waver, Belgium
PoseFM: Relative Camera Pose Estimation Through Flow Matching
Apr 24, 2026Dominik Kuczkowski, Laura RuotsalainenRelative Pose Estimation Camera Pose Estimation
Department of Computer Science University of Helsinki Finland
Revisiting Geometric Obfuscation with Dual Convergent Lines for Privacy-Preserving Image Queries in Visual Localization
Apr 24, 2026Jeonggon Kim, Heejoon Moon, Je Hyeong HongCamera Pose Estimation Privacy-Preserving ML
Dept. Electronic Engineering, Hanyang University · Dept. Artificial Intelligence, Hanyang University
Unlocking the Power of Critical Factors for 3D Visual Geometry Estimation
Apr 23, 2026Guangkai Xu, Hua Geng, Huanyi Zheng +4Multi-View Consistency Depth Estimation
State Key Lab of CAD & CG, Zhejiang University · Tsinghua University · Ant Group

May 25, 2026, cs.CVJ/K move · Enter open · S save

Global Structure-from-Motion Meets Feedforward Reconstruction

Linfei Pan, Johannes Schönberger, Marc Pollefeys

ETH Zurich · Meta Reality Labs · ETH Zurich, Microsoft

Multi-View 3D Reconstruction Camera Pose Estimation Visual SLAM Feed-Forward 3D Reconstruction Structure from Motion

Open paper AskPDF arXiv

Structure-from-Motion -- the process of simultaneously estimating camera poses and 3D scene structure from a collection of images -- remains a central challenge in computer vision, with many open problems yet to be solved. Recent advances in feedforward 3D reconstruction have made significant strides in overcoming persistent failure cases of classical SfM methods, particularly in scenarios characterized by low texture, limited overlap, and symmetries. However, while feedforward approaches excel in these challenging conditions, they often face limitations regarding scalability, accuracy, or robustness, and typically fall short of classical methods in standard reconstruction settings. In this work, we systematically analyze these limitations and propose a new Structure-from-Motion pipeline by combining the respective strengths of classical and feedforward methods. Extensive experiments across multiple datasets show the benefits of our approach, achieving state-of-the-art results across a wide range of scenarios. We share our system as an open-source implementation at https://github.com/colmap/gluemap.

Momentum

Related topics

Latest papers 138