Unsupervised Light Field Depth Estimation via Multi-view Feature Matching with Occlusion Prediction

TL;DR

This paper introduces an unsupervised light field depth estimation framework that leverages multi-view feature matching and occlusion prediction to improve accuracy and robustness without requiring depth labels.

Contribution

It proposes a novel unsupervised approach combining a disparity network, occlusion prediction, and a fusion strategy for enhanced depth estimation from light field images.

Findings

Achieves superior accuracy on dense and sparse LF images.

Demonstrates better robustness and generalization on real-world LF images.

Outperforms existing methods in experimental evaluations.

Abstract

Depth estimation from light field (LF) images is a fundamental step for numerous applications. Recently, learning-based methods have achieved higher accuracy and efficiency than the traditional methods. However, it is costly to obtain sufficient depth labels for supervised training. In this paper, we propose an unsupervised framework to estimate depth from LF images. First, we design a disparity estimation network (DispNet) with a coarse-to-fine structure to predict disparity maps from different view combinations. It explicitly performs multi-view feature matching to learn the correspondences effectively. As occlusions may cause the violation of photo-consistency, we introduce an occlusion prediction network (OccNet) to predict the occlusion maps, which are used as the element-wise weights of photometric loss to solve the occlusion issue and assist the disparity learning. With the disparity maps estimated by multiple input combinations, we then propose a disparity fusion strategy based on the estimated errors with effective occlusion handling to obtain the final disparity map with higher accuracy. Experimental results demonstrate that our method achieves superior performance on both the dense and sparse LF images, and also shows better robustness and generalization on the real-world LF images compared to the other methods.