AI Paper Atlas

Research map / 3D vision / Depth and stereo

Zero-shot Depth from Defocus

Yiming Zuo, Hongyu Wen, Venkat Subramanian, Patrick Chen, Karhan Kayan, Mario Bijelic, Felix Heide, Jia Deng

ECCV 2026 · 3D vision › Depth and stereo · approach: Depth from light field and defocus · 1 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 stack attention layer (ablation)FOSSA ViT-S · ZEDD valdelta_1.05: 0.092 -> 0.445Improved
add focus distance embedding (ablation)FOSSA ViT-S · ZEDD valdelta_1.05: 0.090 -> 0.445Improved
collapse at L1=4 instead of L1=2 (ablation)FOSSA ViT-S · ZEDD valdelta_1.05: 0.372 -> 0.445Improved
collapse at L1=6 instead of L1=4 (ablation)FOSSA ViT-S · ZEDD valdelta_1.05: 0.445 -> 0.524Improved
collapse in feature extractor instead of fusing in DPT head (ablation)FOSSA ViT-S · ZEDD valdelta_1.05: 0.061 -> 0.445Improved
add random blur kernel (PSF shape and f-number) during training (ablation)FOSSA ViT-S · ZEDD valdelta_1.25: drops of 21.12%Improved
add random focus distance distribution during training (ablation)FOSSA ViT-S · ZEDD valdelta_1.25: drops of 39.78%Improved
retrain DFF-DFV with FOSSA training data (ablation)DFF-DFV · DIODEdelta_1.25: 11.92% improvementImproved
use FOSSA ViT-B over DFF-DFV retrained on same data (ablation)FOSSA · DIODEAbsRel: 1.331 -> 0.160Improved
use FOSSA instead of DepthPro (ablation)FOSSA ViT-B · ZEDD testAbsRel: 0.201 -> 0.089Improved
use FOSSA instead of DepthPro (ablation)FOSSA ViT-S · Infinigen DefocusAbsRel: 0.176 -> 0.085Improved
finetune on DDFF instead of zero-shot (ablation)FOSSA ViT-B · DDFFMSE (x1e-4): 12.9 -> 2.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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