期刊
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
卷 -, 期 -, 页码 11460-11470出版社
IEEE COMPUTER SOC
DOI: 10.1109/CVPR46437.2021.01130
关键词
-
资金
- Science and Technology Innovation 2030 -New Generation Artificial Intelligence Major Project [2018AAA0100904]
- NSFC [U19B2043]
- Artificial Intelligence Research Foundation of Baidu Inc.
- HIKVision
- Horizon Robotics
The study introduces a full-resolution correspondence learning approach for image translation, utilizing a hierarchical strategy and PatchMatch algorithm. By employing ConvGRU module and historical estimates, the current correspondence can be refined effectively. Experimental results demonstrate that CoCosNet v2 outperforms state-of-the-art literature in generating high-resolution images.
We present the full-resolution correspondence learning for cross-domain images, which aids image translation. We adopt a hierarchical strategy that uses the correspondence from coarse level to guide the fine levels. At each hierarchy, the correspondence can be efficiently computed via PatchMatch that iteratively leverages the matchings from the neighborhood. Within each PatchMatch iteration, the ConvGRU module is employed to refine the current correspondence considering not only the matchings of larger context but also the historic estimates. The proposed CoCosNet v2, a GRU-assisted PatchMatch approach, is fully differentiable and highly efficient. When jointly trained with image translation, full-resolution semantic correspondence can be established in an unsupervised manner, which in turn facilitates the exemplar-based image translation. Experiments on diverse translation tasks show that CoCosNet v2 performs considerably better than state-of-the-art literature on producing high-resolution images.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据