AI Paper Atlas

Research map / 3D vision / Depth and stereo

FoundDP: Revisiting Weak Disparity Observability in Dual-Pixel Depth Estimation

fengchen he, Hao Xu, Dayang Zhao, Tingwei Quan, Shaoqun zeng

ECCV 2026 · 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
add Structure Refinement (SR) module (ablation)DDE · NYUDataAI(1): 0.2463 -> 0.2312Improved
add Depth Guidance (DG) module (ablation)DDE · NYUDataAI(1): 0.2463 -> 0.1865Improved
add DG to DDE+SR (ablation)DDE+SR · NYUDataAI(1): 0.2312 -> 0.1475Improved
add SR to DDE+DG (ablation)DDE+DG · NYUDataAcc-1: 0.9348 -> 0.9661Improved
add SR to DDE (ablation)DDE · NYUDataAcc-1: 0.9297 -> 0.9491Improved
add ViT feature alignment (ablation)FoundDP · DP5KAI(1): 0.2741 -> 0.2579Improved
add ViT feature alignment (ablation)FoundDP · DP5KAcc-1: 0.7839 -> 0.7976Improved
add ViT feature alignment (ablation)ViT encoder · ViT feature similarity to clean imagecosine similarity: 0.8737 -> 0.9454Improved

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