Multi-View Geometry

Follow this topic Ask about this topic

Momentum

9 papers in the last four weeks, up 80% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 65

All topics

Double-Helix Active Geometry: LiDAR-Anchored Multi-View Depth with Selective Abstention
Jun 28, 2026Jinwen WenMulti-View Depth Estimation Multi-View Geometry
Independent Researcher
Anatomy-Grounded Synthetic Coronary Angiography for Geometry-Informed Multi-View Matching
Jun 26, 2026In Kyu Lee, Sumin Seo, Jaesik MinMulti-View Geometry Medical Imaging
Medipixel, Inc., Seoul, Republic of Korea · University of California San Diego, La Jolla, USA
ReScene: Structured Indoor Scene Reconstruction from Multi-View Captures
Jun 26, 2026Haoran Xu, Lechao Zhang, Daoguo Dong +2Multi-View Geometry 3D Reconstruction
School of Computer Science and Technology, East China Normal University · Institute of Trustworthy Embodied AI, Fudan University
Rolling Shutter Relative Pose Estimation Made Practical
Jun 25, 2026Daniel BarathMulti-View Geometry Relative Pose Estimation
ETH Zürich, Computer Vision and Geometry Group · Google Zurich · HUN-REN SZTAKI, Budapest, Hungary
Calousel: Extrinsic Calibration of Non-overlapping Multi-camera Systems from Pure Rotation
Jun 24, 2026Gwanhyeong Song, Chaehyeon Song, Ayoung KimMulti-View Geometry Camera Pose Estimation
Dept. of Mechanical Engineering, SNU, Seoul, S. Korea
Pose Anything Anywhere:Model-free Object Poses from Arbitrary References
Jun 22, 2026Hongli Xu, Jiaqi Hu, Junwen Huang +5Multi-View Geometry Object Pose Estimation
Technical University of Munich · Siemens AG · Munich Center for Machine Learning (MCML) +2
OmniSpace: Efficient Geometry Awareness for Autonomous Vehicles MLLMs
Jun 21, 2026Hao Vo, Phu Loc Nguyen, Khoa Vo +7Multi-View Geometry Vision-Language Models
University of Arkansas, USA · Google Research, Google · University of Liverpool, UK +1
Geometric Consistency Protocol for Foundation Model Features in Multi-View Satellite Imagery
Jun 16, 2026Qiyan Luo, Jie Yang, Yingdong Pi +2Remote Sensing Image Understanding Multi-View Consistency
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University
RANSAC Scoring Done Right
Jun 12, 2026James Pritts, Felix Seegräber, Kevin KöserMulti-View Geometry Robust Estimation
Marine Data Science, Institut für Informatik Kiel University, Germany
Efficient Minimal Solvers for Visual-Inertial Relative Pose Estimation in Multi-Camera Systems
Jun 8, 2026Tao Li, Zhenbao Yu, Banglei Guan +2Multi-View Geometry Relative Pose Estimation
College of Aerospace Science and Engineering, Naval Aviation University, Yantai 264000, China · College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410000, China
Virtual-point-based Solutions to Handle Generalized Absolute Pose Problem
Jun 8, 2026Bin Li, Banglei Guan, Shunkun Liang +1Multi-View Geometry Camera Pose Estimation
Hunan Institute of Advanced Technology, Changsha 410205, China · College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China · Hunan Provincial Key Laboratory of Image Measurement and Vision Navigation, Changsha 410073, China
See More, Match Better: Multi-Source Feature Fusion for Two-View Correspondence Learning
Jun 8, 2026Xiaojie Li, Xin Jiang, Luanyuan Dai +3Multi-View Geometry
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China · State Key Laboratory of Communication Content Cognition, People’s Daily Online, Beijing, 100733, China · School of Information Science and Technology, University of Science and Technology of China, Hefei 230026, China
G2G: Exploiting Intra-Group Geometry for Inter-Group Pose Estimation
Jun 6, 2026Yufei Wei, Shuhao Ye, Chenxiao Hu +5Multi-View Geometry Relative Pose Estimation
State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China · Zhejiang Humanoid Robot Innovation Center Co., Ltd., Ningbo, China · School of Information Science and Engineering, Hangzhou Normal University, Hangzhou, China
GeM-NR: Geometry-Aware Multi-View Editing for Nonrigid Scene Changes
Jun 3, 2026Josef Bengtson, Yaroslava Lochman, Fredrik KahlMulti-View Consistency Multi-View Geometry
Chalmers University of Technology
SAMatcher: Co-Visibility Modeling with Segment Anything for Robust Feature Matching
Jun 2, 2026Xu Pan, Qiyuan Ma, Mingyue Dong +3Multi-View Geometry Image Matching
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS), Wuhan University, Wuhan, P. R. China · National Key Laboratory of Space Target Awareness, Space Engineering University, Beijing, P. R. China
Joint Multi-Camera LiDAR Extrinsic Calibration via Learned Pairwise Initialization and Geometric Refinement
May 29, 2026Aziz Al-Najjar, Marzieh Amini, James R. Green +1Multi-View Geometry Bundle Adjustment
Department of System and Computer Engineering, Carleton University, Ottawa, Canada
Mesh-Aware Epipolar Matching for Multi-View Multi-Person 3D Pose Estimation in Basketball
May 28, 2026Li Yin, Qin Haobin, Tomohiro Suzuki +3Multi-View Geometry 3D Reconstruction
Graduate School of Informatics, Nagoya University, Chikusa-ku, Nagoya, Aichi, Japan. · Department of Information Engineering, Faculty of Science and Technology, Keio University, Hiyoshi, Yokohama, Kanagawa, Japan. · RIKEN Center for Advanced Intelligence Project, 1-5, Yamadaoka, Suita, Osaka, Japan.
StereoGenBench: A Synthetic Multi-Camera Benchmark for Stereo Generation under Controlled Baseline Regimes
May 22, 2026Yangzhi Cui, Feng Qiao, Nathan JacobsMulti-View Geometry Synthetic Benchmark Generation
Washington University in St. Louis
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
Can These Views Be One Scene? Evaluating Multiview 3D Consistency when 3D Foundation Models Hallucinate
May 18, 2026Soumava Paul, Prakhar Kaushik, Alan Yuille3D Foundation Models Multi-View Consistency
CCVL, Johns Hopkins University
CalibAnyView: Beyond Single-View Camera Calibration in the Wild
May 14, 2026Boying Li, Cheng Zhang, Weirong Chen +3Multi-View Consistency Multi-View Geometry
Monash University · Technical University of Munich · Mohamed bin Zayed University of Artificial Intelligence
Agentic Pipeline for Self-Synchronized Multiview Joint Angle Monitoring in Uncalibrated Environments
May 14, 2026Juncheng Yu, Lusi A, Haoxuan Xie +1Multi-View Geometry Markerless Motion Capture
National Engineering Research Center of Neuromodulation, School of Aerospace Engineering, Tsinghua University, Beijing 100084, China
PrePARE: Pre-AA Token Pruning for Frozen Multi-View Geometry Transformers
May 8, 2026Haotang Li, Zhenyu Qi, Shaohan Henry Wang +5Multi-View Geometry Efficient ViTs
University of Arizona · East Carolina University · Augusta University +1
Implicit Multi-Camera System Calibration Using Gaussian Processes
May 8, 2026Ivan De Boi, Bart Ribbens, Veronika Golanova +2Multi-View Geometry Camera Calibration
1InViLab, University of Antwerp, Groenenborgerlaan 179, Antwerp, 2020, Belgium.
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
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
AirZoo: A Unified Large-Scale Dataset for Grounding Aerial Geometric 3D Vision
Apr 29, 2026Xiaoya Cheng, Rouwan Wu, Xinyi Liu +6Remote Sensing Image Understanding Multi-View Geometry
National University of Defense Technology, Changsha, China · National Key Laboratory of Advanced Guidance and Control Technology, Changsha, China · Singapore University of Technology and Design, Singapore
Unconstrained Multi-view Human Pose Estimation with Algebraic Priors
Apr 27, 2026Xiaolin Qin, Qianlei Wang, Jiacen Liu +3Multi-View Geometry 3D Human Pose Estimation
Chengdu Institute of Computer Applications, Chinese Academy of Sciences, Chengdu 610213, China · School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 101408, China · School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China. +2

Jun 28, 2026, cs.CVJ/K move · Enter open · S save

Double-Helix Active Geometry: LiDAR-Anchored Multi-View Depth with Selective Abstention

Jinwen Wen

Independent Researcher

Multi-View Depth Estimation Multi-View Geometry Metric Depth Estimation Depth Estimation Camera-LiDAR Fusion

Open paper AskPDF arXiv

Consumer depth sensors such as the LiDAR scanner on recent iPhones provide metric range, but their useful range is short and their returns are sparse. We present DH-Active, a lightweight, training-free geometry back-end that treats the sensor as a metric ruler rather than the sole source of depth. Near-field returns anchor the metric relative pose of two views through PnP; visually trackable samples without a valid depth return are then triangulated under that pose. A parallax/reprojection gate abstains wherever the geometry is ill-conditioned, leaving an explicit hole and a selective score instead of forcing an estimate. The measured core front end, including spiral sampling, sparse back-projection, and hole taxonomy but excluding preprocessing and multi-view recovery, runs at 1.11 ms median latency on CPU (OpenCV using 14 threads), about 38 times faster than a DINOv2-L visual branch on GPU in our timing setup. Across two iPhone captures and the public TUM RGB-D and ARKitScenes benchmarks, held-out depth is recovered at 1.4 to 6.7 percent median relative error. In a controlled ARKitScenes protocol that uses only returns within 2 m to set scale and an independent laser scan as ground truth, DH-Active achieves 64.2 percent scene-median coverage of evaluable far-field candidates at 13.4 percent scene-median relative error; direct triangulation from the device trajectory is not usable. We also report the alternatives that failed in our tests: single-frame defocus, classical focus-stack depth, defocus-LiDAR fusion, point-to-point ICP over a good visual-inertial track, and attention-to-holes resampling. A 1.26 B learned model remains more accurate after oracle scale alignment. The contribution here is narrower: metric sparse depth, explicit abstention, zero learned parameters, and near-millisecond CPU cost.

Momentum

Related topics

Latest papers 65