View-consistent 4D Light Field Depth Estimation
This addresses the challenge of consistent depth estimation in light fields, which is important for applications like 3D reconstruction and virtual reality, but is incremental over prior methods that focused only on the central view.
The paper tackles the problem of view-consistent depth estimation across all sub-aperture images in a light field, achieving competitive quantitative metrics and qualitative performance on synthetic and real-world data.
We propose a method to compute depth maps for every sub-aperture image in a light field in a view consistent way. Previous light field depth estimation methods typically estimate a depth map only for the central sub-aperture view, and struggle with view consistent estimation. Our method precisely defines depth edges via EPIs, then we diffuse these edges spatially within the central view. These depth estimates are then propagated to all other views in an occlusion-aware way. Finally, disoccluded regions are completed by diffusion in EPI space. Our method runs efficiently with respect to both other classical and deep learning-based approaches, and achieves competitive quantitative metrics and qualitative performance on both synthetic and real-world light fields