Abstract | ||
---|---|---|
Estimating homography from an image pair is a fundamental problem in image alignment. Unsupervised learning methods have received increasing attention in this field due to their promising performance and label-free training. However, existing methods do not explicitly consider the problem of plane-induced parallax, which will make the predicted homography compromised on multiple planes. In this work, we propose a novel method HomoGAN to guide unsupervised homography estimation to focus on the dominant plane. First, a multi-scale transformer network is designed to predict homography from the feature pyramids of input images in a coarse-to-fine fashion. Moreover, we propose an unsupervised GAN to impose coplanarity constraint on the predicted homography, which is realized by using a generator to predict a mask of aligned regions, and then a discriminator to check if two masked feature maps are induced by a single homography. To validate the effectiveness of HomoGAN and its components, we conduct extensive experiments on a large-scale dataset, and results show that our matching error is 22% lower than the previous SOTA method. Code is available at https://github.com/megvii-research/HomoGAN |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/CVPR52688.2022.01714 | IEEE Conference on Computer Vision and Pattern Recognition |
Keywords | DocType | Volume |
Low-level vision, Computational photography, Image and video synthesis and generation, Motion and tracking | Conference | 2022 |
Issue | Citations | PageRank |
1 | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mingbo Hong | 1 | 0 | 0.34 |
Yuhang Lu | 2 | 0 | 0.34 |
Nianjin Ye | 3 | 0 | 0.68 |
Chun-Yu Lin | 4 | 379 | 74.29 |
Qijun Zhao | 5 | 0 | 0.34 |
Shuaicheng Liu | 6 | 363 | 28.26 |