A cycle-consistent reciprocal network for visual correspondence

• Main Authors: He, Zhiquan, Zheng, Donghong, Cao, Wenming
• Format: Conference Proceeding
• Language: English
• Published: SPIE 28.12.2022
• ISBN: 9781510661240; 1510661247
• ISSN: 0277-786X
• DOI: 10.1117/12.2662501

Visual correspondence refers to building dense correspondences between two or more images of the same category. Ideally, the predicted keypoints output by the model can be back to the source image’s keypoints through the same type of network. However, in practical situations, the predicted keypoints usually do not perfectly map back to the source image keypoints. In order to strengthen the cycle-consistency of the model, we propose a cycle-consistent reciprocal network. The network uses joint loss functions to alternately train forward and inverse models, which makes the two models subject to cycle constraints and perform better with the help of each other. Experiment results demonstrate the performance of the model is improved on three popular benchmarks and set a new state-of-the-art on the benchmark of PF-WILLOW.