Single Image Depth Estimation Based on Spectral Consistency and Predicted View

Anonymous

Keywords: Single Image Depth Estimation, Stereo Matching, View Prediction, Unsupervised Learning

Abstract: Single image depth estimation is a critical issue for robot vision, augmented reality, and many other applications when an image sequence is not available. Self-supervised single image depth estimation models target at predicting accurate disparity map just from one single image without ground truth supervision or stereo image pair during real applications. Compared with direct single image depth estimation, single image stereo algorithm can generate the depth from different camera perspectives. In this paper, we propose a novel architecture to infer accurate disparity by leveraging both spectral-consistency based learning model and view-prediction based stereo reconstruction algorithm. Direct spectral-consistency based method can avoid false positive matching in smooth regions. Single image stereo can preserve more distinct boundaries from another camera perspective. By learning confidence map and designing a fusion strategy, the two disparities from two approaches are able to be effectively fused to produce the refined disparity. Extensive experiments indicate that our method exploits both advantages of spectral consistency and view prediction, especially in constraining boundaries and correcting wrong predicting regions.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: We propose a novel architecture to infer accurate disparity by leveraging both spectral-consistency based learning model and view-prediction based stereo reconstruction algorithm.