2021/11/08 by Byeongjun Park, Park, Byeongjun, Taekyung Kim +5
Computer Science · Engineering · #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Processing Techniques and Applications #Optical measurement and interference techniques
paper · pdf · doi:10.48550/arxiv.2111.04310
openalex publication_date 2021/11/08 · openalex created_date 2021/11/22 · openalex updated_date 2026/07/28
Photometric consistency loss is one of the representative objective functions commonly used for self-supervised monocular depth estimation. However, this loss often causes unstable depth predictions in textureless or occluded regions due to incorrect guidance. Recent self-supervised learning approaches tackle this issue by utilizing feature representations explicitly learned from auto-encoders, expecting better discriminability than the input image. Despite the use of auto-encoded features, we observe that the method does not embed features as discriminative as auto-encoded features. In this paper, we propose residual guidance loss that enables the depth estimation network to embed the discriminative feature by transferring the discriminability of auto-encoded features. We conducted experiments on the KITTI benchmark and verified our method's superiority and orthogonality on other state-of-the-art methods.