AI Paper Atlas

Research map / 3D vision / Depth and stereo

Epipolar Consistent Attention Aggregation Network for Unsupervised Light Field Disparity Estimation

Chen Gao, Shuo Zhang, Youfang Lin

ICCV 2025 · 3D vision › Depth and stereo · approach: Depth from light field and defocus · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace linear upsampling with deconvolution (epipolar consistent upsample) (ablation)ECAAN5 · SLFD LionMSE x100 / Bp(0.3): 2.48/14.69 -> 2.06/6.79Improved
integrate at attention level with linear upsampling instead of averaging disparities (ablation)ECAAN5 · SLFD LionMSE x100 / Bp(0.3): 4.96/21.26 -> 2.48/14.69Improved
add COFA occlusion-free aggregation block (ablation)ECAAN5 · SLFD LionMSE x100 / Bp(0.3): 2.06/6.79 -> 0.08/1.13Improved
add occlusion masks to the unsupervised loss (versus none) (ablation)ECAAN5 · SLFD LionMSE x100 / Bp(0.3): 0.26/2.17 -> 0.08/1.13Improved
use full occlusion masks instead of only sub-occlusion masks (ablation)ECAAN5 · SLFD LionMSE x100 / Bp(0.3): 0.16/1.46 -> 0.08/1.13Improved
use all 5x5 views instead of 3x3 viewsECAAN · SLFD LionMSE x100: 0.173 -> 0.087Improved
use all 5x5 views instead of 3x3 viewsECAAN · SLFD Toy bricksMSE x100: 0.332 -> 0.408Hurt
use ECAAN3 instead of UnMVFMECAAN3 · SLFD Rooster clockMSE x100: 0.261 -> 0.177Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy