In this work, we explore new perspectives on cross-view completion learning by drawing an analogy to self-supervised correspondence learning. Through our analysis, we demonstrate that the cross-attention map within cross-view completion models captures correspondence more effectively than other correlations derived from encoder or decoder features. We verify the effectiveness of the cross-attention map by evaluating on both zero-shot matching and learning-based geometric matching and multi-frame depth estimation. Project page is available at https://cvlab-kaist.github.io/ZeroCo/.
@article{arxiv.2412.09072,
title = {Cross-View Completion Models are Zero-shot Correspondence Estimators},
author = {Honggyu An and Jinhyeon Kim and Seonghoon Park and Jaewoo Jung and Jisang Han and Sunghwan Hong and Seungryong Kim},
journal= {arXiv preprint arXiv:2412.09072},
year = {2024}
}