Edge-aware Bidirectional Diffusion for Dense Depth Estimation from Light Fields

TL;DR

This paper introduces an edge-aware bidirectional diffusion algorithm that leverages sparse depth edges and gradients from light fields to produce fast, accurate dense depth maps by disambiguating true depth edges from texture edges.

Contribution

It proposes a novel bidirectional diffusion method that uses depth edges and gradients to improve dense depth estimation from light fields, addressing edge ambiguity.

Findings

Achieves accurate dense depth maps from sparse depth edges.

Effectively separates depth edges from texture edges.

Provides a fast and reliable depth estimation process.

Abstract

We present an algorithm to estimate fast and accurate depth maps from light fields via a sparse set of depth edges and gradients. Our proposed approach is based around the idea that true depth edges are more sensitive than texture edges to local constraints, and so they can be reliably disambiguated through a bidirectional diffusion process. First, we use epipolar-plane images to estimate sub-pixel disparity at a sparse set of pixels. To find sparse points efficiently, we propose an entropy-based refinement approach to a line estimate from a limited set of oriented filter banks. Next, to estimate the diffusion direction away from sparse points, we optimize constraints at these points via our bidirectional diffusion method. This resolves the ambiguity of which surface the edge belongs to and reliably separates depth from texture edges, allowing us to diffuse the sparse set in a depth-edge and occlusion-aware manner to obtain accurate dense depth maps.