Occlusion-Aware Cost Constructor for Light Field Depth Estimation
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.
Code (1)
Tasks
Depth EstimationSimilar Papers 제목 키워드 기반
OccCasNet: Occlusion-aware Cascade Cost Volume for Light Field Depth Estimation
Light field (LF) depth estimation is a crucial task with numerous practical applications. However, mainstream methods based on the multi-view stereo (MVS) are resource-intensive and time-consuming as they need to constru…
Depth EstimationDisparity EstimationDSER: Spectral Epipolar Representation for Efficient Light Field Depth Estimation
Dense light field depth estimation remains challenging due to sparse angular sampling, occlusion boundaries, textureless regions, and the cost of exhaustive multi-view matching. We propose \emph{Deep Spectral Epipolar Re…
Depth EstimationRobust Light Field Depth Estimation for Noisy Scene With Occlusion
Light field depth estimation is an essential part of many light field applications. Numerous algorithms have been developed using various light field characteristics. However, conventional methods fail when handling nois…
Depth EstimationSiMA-Hand: Boosting 3D Hand-Mesh Reconstruction by Single-to-Multi-View Adaptation
Estimating 3D hand mesh from RGB images is a longstanding track, in which occlusion is one of the most challenging problems. Existing attempts towards this task often fail when the occlusion dominates the image space. In…
Occlusion-aware Unsupervised Learning of Depth from 4-D Light Fields
Depth estimation is a fundamental issue in 4-D light field processing and analysis. Although recent supervised learning-based light field depth estimation methods have significantly improved the accuracy and efficiency o…
Depth EstimationDepth Prediction