arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision

2025-11-07 至 2025-11-07 共收录 3
2311.16304 2025-11-07 cs.CV

Robust Self-calibration of Focal Lengths from the Fundamental Matrix

Viktor Kocur, Daniel Kyselica, Zuzana Kukelova

机构 * Faculty of Mathematics, Physics and Informatics, Comenius University in Bratislava(数学、物理与信息学系,布拉迪斯拉瓦康门大学) Visual Recognition Group, Faculty of Electrical Engineering, Czech Technical University in Prague(视觉识别组,布拉格捷克技术大学)

Comments Pubslished in CVPR 2024. Accepted: 26.2.2024. Published: 16.6.2024. This work was funded by the Horizon-Widera-2021 European Twinning project TERAIS G.A. n. 101079338. Code available: https://github.com/kocurvik/robust_self_calibration and https://doi.org/10.5281/zenodo.14584742

详情

展开后加载摘要…

URL PDF HTML 收藏
2303.16078 2025-11-07 cs.CV

Practical solutions to the relative pose of three calibrated cameras

Charalambos Tzamos, Viktor Kocur, Yaqing Ding, Daniel Barath, Zuzana Berger Haladova, Torsten Sattler, Zuzana Kukelova

机构 * Visual Recognition Group, Faculty of Electrical Engineering, Czech Technical University in Prague(视觉识别组,电气工程系,布拉格捷克技术大学) Faculty of Mathematics, Physics and Informatics, Comenius University in Bratislava(数学、物理和信息学系,布拉迪斯拉发康门尼乌斯大学) ETH Zürich (Zurich), HUN-REN SZTAKI (Budapest)(苏黎世ETH,匈牙利-中国SZTAKI(布达佩斯)) Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague(捷克信息学、机器人学与自动控制研究所,布拉格捷克技术大学)

Comments Paper presented at CVPR 2025 (DOI: 10.1109/CVPR52734.2025.02041). Code available at https://github.com/kocurvik/threeview and https://doi.org/10.5281/zenodo.16599943. Data available at https://doi.org/10.5281/zenodo.16603086

详情

展开后加载摘要…

URL PDF HTML 收藏
2401.01887 2025-11-07 cs.CV

LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry

Weirong Chen, Le Chen, Rui Wang, Marc Pollefeys

机构 * TU Munich(慕尼黑技术大学) Munich Center for Machine Learning(慕尼黑机器学习中心) MPI for Intelligent Systems(智能系统研究所) Microsoft(微软公司)

Comments Accepted to CVPR 2024. Project page: https://wrchen530.github.io/projects/leapvo

详情

展开后加载摘要…

URL PDF HTML 收藏