Accurate Light Field Depth Estimation with Superpixel Regularization over Partially Occluded Regions

TL;DR

This paper introduces a novel light field depth estimation method that effectively handles occlusions by regularizing confidence maps and edge weights using superpixel-based detection of partially occluded regions, leading to improved accuracy.

Contribution

The proposed framework uniquely combines superpixel regularization with confidence and edge weight manipulation to better address occlusions in depth estimation.

Findings

Outperforms state-of-the-art in disparity error rate

Improves occlusion boundary detection precision-recall

Preserves intricate scene features better

Abstract

Depth estimation is a fundamental problem for light field photography applications. Numerous methods have been proposed in recent years, which either focus on crafting cost terms for more robust matching, or on analyzing the geometry of scene structures embedded in the epipolar-plane images. Significant improvements have been made in terms of overall depth estimation error; however, current state-of-the-art methods still show limitations in handling intricate occluding structures and complex scenes with multiple occlusions. To address these challenging issues, we propose a very effective depth estimation framework which focuses on regularizing the initial label confidence map and edge strength weights. Specifically, we first detect partially occluded boundary regions (POBR) via superpixel based regularization. Series of shrinkage/reinforcement operations are then applied on the label confidence map and edge strength weights over the POBR. We show that after weight manipulations, even a low-complexity weighted least squares model can produce much better depth estimation than state-of-the-art methods in terms of average disparity error rate, occlusion boundary precision-recall rate, and the preservation of intricate visual features.