7 papers · 1 filter
Fast Full-frame Video Stabilization with Iterative Optimization
Weiyue Zhao, Xin Li, Zhan Peng +4
Video stabilization refers to the problem of transforming a shaky video into a visually pleasing one. The question of how to strike a good trade-off between visual quality and comp…
Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells
Xinyi Ye, Weiyue Zhao, Tianqi Liu +3
Learning-based multi-view stereo (MVS) methods deal with predicting accurate depth maps to achieve an accurate and complete 3D representation. Despite the excellent performance, ex…
Learning Probabilistic Coordinate Fields for Robust Correspondences
Weiyue Zhao, Hao Lu, Xinyi Ye +2
We introduce Probabilistic Coordinate Fields (PCFs), a novel geometric-invariant coordinate representation for image correspondence problems. In contrast to standard Cartesian coor…
A2B: Anchor to Barycentric Coordinate for Robust Correspondence
Weiyue Zhao, Hao Lu, Zhiguo Cao +1
There is a long-standing problem of repeated patterns in correspondence problems, where mismatches frequently occur because of inherent ambiguity. The unique position information a…
LRF-Net: Learning Local Reference Frames for 3D Local Shape Description and Matching
Angfan Zhu, Jiaqi Yang, Weiyue Zhao +1
The local reference frame (LRF) acts as a critical role in 3D local shape description and matching. However, most of existing LRFs are hand-crafted and suffer from limited repeatab…
Iterative Clustering with Game-Theoretic Matching for Robust Multi-consistency Correspondence
Chen Zhao, Jiaqi Yang, Ke Xian +2
Matching corresponding features between two images is a fundamental task to computer vision with numerous applications in object recognition, robotics, and 3D reconstruction. Curre…