OccCasNet: Occlusion-aware Cascade Cost Volume for Light Field Depth Estimation

TL;DR

OccCasNet introduces an occlusion-aware cascade cost volume approach for light field depth estimation, significantly improving accuracy and efficiency by reducing sampling and incorporating occlusion maps, outperforming state-of-the-art methods.

Contribution

The paper proposes a novel occlusion-aware cascade cost volume technique that enhances light field depth estimation by balancing accuracy and computational efficiency.

Findings

Achieves top performance on HCI 4D benchmark

Outperforms existing methods in MSE and Q25 metrics

Reduces resource consumption compared to traditional multi-view stereo methods

Abstract

Light field (LF) depth estimation is a crucial task with numerous practical applications. However, mainstream methods based on the multi-view stereo (MVS) are resource-intensive and time-consuming as they need to construct a finer cost volume. To address this issue and achieve a better trade-off between accuracy and efficiency, we propose an occlusion-aware cascade cost volume for LF depth (disparity) estimation. Our cascaded strategy reduces the sampling number while keeping the sampling interval constant during the construction of a finer cost volume. We also introduce occlusion maps to enhance accuracy in constructing the occlusion-aware cost volume. Specifically, we first obtain the coarse disparity map through the coarse disparity estimation network. Then, the sub-aperture images (SAIs) of side views are warped to the center view based on the initial disparity map. Next, we propose photo-consistency constraints between the warped SAIs and the center SAI to generate occlusion maps for each SAI. Finally, we introduce the coarse disparity map and occlusion maps to construct an occlusion-aware refined cost volume, enabling the refined disparity estimation network to yield a more precise disparity map. Extensive experiments demonstrate the effectiveness of our method. Compared with state-of-the-art methods, our method achieves a superior balance between accuracy and efficiency and ranks first in terms of MSE and Q25 metrics among published methods on the HCI 4D benchmark. The code and model of the proposed method are available at https://github.com/chaowentao/OccCasNet.