Cross-View Completion Models are Zero-shot Correspondence Estimators

Figure 1 . Cross-view completion models [92, 93] are zero-shot correspondence estimators. Given a pair of images consisting of target (left) and source (right) images, we visualize the attended region in the source image corresponding to a query point marked in the target image in blue, where the point with the highest attention is marked in red. Although cross-view completion models [92, 93] are not trained with correspondence-supervision, its cross-attention map already establishes precise correspondences.