English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

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

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