2022/03/03 by Yingqian Wang, Wang, Yingqian, Longguang Wang +9 · 3 citations
Computer Science · #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Enhancement Techniques #Optical measurement and interference techniques
paper · pdf · doi:10.48550/arxiv.2203.01576
openalex publication_date 2022/03/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Matching cost construction is a key step in light field (LF) depth estimation, but was rarely studied in the deep learning era. Recent deep learning-based LF depth estimation methods construct matching cost by sequentially shifting each sub-aperture image (SAI) with a series of predefined offsets, which is complex and time-consuming. In this paper, we propose a simple and fast cost constructor to construct matching cost for LF depth estimation. Our cost constructor is composed by a series of convolutions with specifically designed dilation rates. By applying our cost constructor to SAI arrays, pixels under predefined disparities can be integrated and matching cost can be constructed without using any shifting operation. More importantly, the proposed cost constructor is occlusion-aware and can handle occlusions by dynamically modulating pixels from different views. Based on the proposed cost constructor, we develop a deep network for LF depth estimation. Our network ranks first on the commonly used 4D LF benchmark in terms of the mean square error (MSE), and achieves a faster running time than other state-of-the-art methods.