AI Paper Atlas

Research map / 3D vision / Depth and stereo

Bridging Unsupervised and Supervised Depth From Focus via All-in-Focus Supervision

Ning-Hsu Wang, Ren Wang, Yu-Lun Liu, Yu-Hao Huang, Yu-Lin Chang, Chia-Ping Chen, Kevin Jou

ICCV 2021 · 3D vision › Depth and stereo · approach: Depth from light field and defocus · 48 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
use 3D convolution instead of 2D convolution (ablation)Depth-from-focus attention network · 4D Light Field DatasetMAE: 0.1070 -> 0.0788Improved
use 3D convolution instead of 2D convolution (ablation)Depth-from-focus attention network · 4D Light Field DatasetBumpiness: 2.1435 -> 1.5776Improved
add the shared attention mechanism (ablation)Depth-from-focus attention network · 4D Light Field Dataset (3D)MAE: 0.0851 -> 0.0788Improved
add the shared attention mechanism (ablation)Depth-from-focus attention network · 4D Light Field Dataset (3D)MSE: 0.0461 -> 0.0472No clear effect
add the shared attention mechanism (ablation)Depth-from-focus attention network · 4D Light Field Dataset (3D)Bumpiness: 2.3168 -> 1.5776Improved
add smoothness loss to unsupervised training (stack 10) (ablation)Depth-from-focus attention network · 4D Light Field DatasetMAE: 0.2425 -> 0.1671Improved
add smoothness loss to unsupervised training (stack 37) (ablation)Depth-from-focus attention network · 4D Light Field DatasetMAE: 0.2099 -> 0.1116Improved
increase focal stack size from 10 to 37 in unsupervised training (ablation)Depth-from-focus attention network · 4D Light Field DatasetMAE: 0.1671 -> 0.1116Improved
use supervised depth instead of AiF supervision (stack 10, no smoothness) (ablation)Depth-from-focus attention network · 4D Light Field DatasetMAE: 0.2425 -> 0.0788Improved
train with arbitrary stack sizes instead of fixed size 10 (ablation)Depth-from-focus attention network · 4D Light Field Dataset, varying test stack sizedisparity errorImproved
use supervised ours instead of DefocusNetDepth-from-focus attention network · 4D Light Field DatasetMSE: 0.0593 -> 0.0472Improved
use supervised ours instead of DefocusNetDepth-from-focus attention network · DefocusNet datasetMAE: 0.0637 -> 0.0549Improved

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