Fast and Accurate Depth Estimation from Sparse Light Fields

TL;DR

This paper introduces a fast, parallelized method for dense depth estimation from sparse light fields using superpixels and iterative refinement, achieving high accuracy with reduced computational cost.

Contribution

The method employs superpixel segmentation and parallel optimization to significantly speed up depth reconstruction from sparse light fields while maintaining high accuracy.

Findings

Depth maps are generated in about one second per HD view.

The approach achieves accuracy comparable to state-of-the-art methods.

Effective in textured, textureless, and occluded regions.

Abstract

We present a fast and accurate method for dense depth reconstruction from sparsely sampled light fields obtained using a synchronized camera array. In our method, the source images are over-segmented into non-overlapping compact superpixels that are used as basic data units for depth estimation and refinement. Superpixel representation provides a desirable reduction in the computational cost while preserving the image geometry with respect to the object contours. Each superpixel is modeled as a plane in the image space, allowing depth values to vary smoothly within the superpixel area. Initial depth maps, which are obtained by plane sweeping, are iteratively refined by propagating good correspondences within an image. To ensure the fast convergence of the iterative optimization process, we employ a highly parallel propagation scheme that operates on all the superpixels of all the images at once, making full use of the parallel graphics hardware. A few optimization iterations of the energy function incorporating superpixel-wise smoothness and geometric consistency constraints allows to recover depth with high accuracy in textured and textureless regions as well as areas with occlusions, producing dense globally consistent depth maps. We demonstrate that while the depth reconstruction takes about a second per full high-definition view, the accuracy of the obtained depth maps is comparable with the state-of-the-art results.