no code implementations • 19 Apr 2024 • Zhan Peng, Xinyi Ye, Weiyue Zhao, Tianqi Liu, Huiqiang Sun, Baopu Li, Zhiguo Cao
In this paper, we present RStab, a novel framework for video stabilization that integrates 3D multi-frame fusion through volume rendering.
1 code implementation • ICCV 2023 • Tianqi Liu, Xinyi Ye, Weiyue Zhao, Zhiyu Pan, Min Shi, Zhiguo Cao
This constraint reduces the 2D search space into the epipolar line in stereo matching.
Ranked #3 on 3D Reconstruction on DTU
1 code implementation • ICCV 2023 • Weiyue Zhao, Xin Li, Zhan Peng, Xianrui Luo, Xinyi Ye, Hao Lu, Zhiguo Cao
Video stabilization refers to the problem of transforming a shaky video into a visually pleasing one.
1 code implementation • ICCV 2023 • Xinyi Ye, Weiyue Zhao, Tianqi Liu, Zihao Huang, Zhiguo Cao, Xin Li
Learning-based multi-view stereo (MVS) methods deal with predicting accurate depth maps to achieve an accurate and complete 3D representation.
no code implementations • 7 Jun 2023 • Weiyue Zhao, Hao Lu, Xinyi Ye, Zhiguo Cao, Xin Li
We introduce Probabilistic Coordinate Fields (PCFs), a novel geometric-invariant coordinate representation for image correspondence problems.
no code implementations • 5 Jun 2023 • Weiyue Zhao, Hao Lu, Zhiguo Cao, Xin Li
This approach offers a new perspective to alleviate the problem of repeated patterns and emphasizes the importance of choosing coordinate representations for feature correspondences.
no code implementations • 11 Apr 2023 • Xianrui Luo, Juewen Peng, Weiyue Zhao, Ke Xian, Hao Lu, Zhiguo Cao
Benefiting from the multi-camera module in modern smartphones, we introduce a new task of AIF synthesis from main (wide) and ultra-wide cameras.
no code implementations • 28 Mar 2023 • Xinyi Ye, Weiyue Zhao, Hao Lu, Zhiguo Cao
It is challenging because of the disorganized spatial distribution of numerous outliers, especially when putative correspondences are largely dominated by outliers.
no code implementations • 22 Jan 2020 • Angfan Zhu, Jiaqi Yang, Weiyue Zhao, Zhiguo Cao
The local reference frame (LRF) acts as a critical role in 3D local shape description and matching.