Homography estimation is erroneous in the case of large-baseline due to the low image overlay and limited receptive field. To address it, we propose a progressive estimation strategy by converting large-baseline homography into multiple intermediate ones, cumulatively multiplying these intermediate items can reconstruct the initial homography. Meanwhile, a semi-supervised homography identity loss, which consists of two components: a supervised objective and an unsupervised objective, is introduced. The first supervised loss is acting to optimize intermediate homographies, while the second unsupervised one helps to estimate a large-baseline homography without photometric losses. To validate our method, we propose a large-scale dataset that covers regular and challenging scenes. Experiments show that our method achieves state-of-the-art performance in large-baseline scenes while keeping competitive performance in small-baseline scenes. Code and dataset are available at https://github.com/megvii-research/LBHomo.
@article{arxiv.2212.02763,
title = {Semi-supervised Deep Large-baseline Homography Estimation with Progressive Equivalence Constraint},
author = {Hai Jiang and Haipeng Li and Yuhang Lu and Songchen Han and Shuaicheng Liu},
journal= {arXiv preprint arXiv:2212.02763},
year = {2022}
}