AI Paper Atlas

Research map / 3D vision / Face and shape

Robust Shape from Focus via Multiscale Directional Dilated Laplacian and Recurrent Network

Khurram Ashfaq, Muhammad Tariq Mahmood

IJCV 2026 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 5 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 the DDL focus volume with a ConvNeXtV2-Atto encoder focus volume (ablation)DDL + GRU pipeline · FTMAE: 2.39 -> 2.03Improved
use DDL (0 params) instead of ResNet-18 encoder (11.2M params) for the focus volume (ablation)GRU depth extractor · FTAcc 1.25: 95.42 -> 95.73Improved
use DDL instead of VGG-16 encoder for the focus volume (ablation)GRU depth extractor · FTMAE: 8.99 -> 2.39Improved
use DDL instead of MobileNetV3 encoder for the focus volume (ablation)GRU depth extractor · FTMAE: 2.10 -> 2.39Hurt
use GRU recurrent depth extraction instead of AiFDNet regressor, same DDL focus volume (ablation)DDL focus volume · FTMAE: 5.45 -> 2.70Improved
use GRU recurrent depth extraction instead of DFV-FV regressor, same DDL focus volume (ablation)DDL focus volume · FTMSE: 370.50 -> 102.17Improved
add progressively larger dilation rates (G1 to G4) to DDL focus volume (ablation)traditional SFF depth extraction · HCI/LFSD/FT under Gaussian, S&P, speckle noiseRMSE / CORRImproved
add larger dilation rate (G2 over G1) to DDL in noise-free case (ablation)traditional SFF depth extraction · HCI and FT, noise-freeRMSE / CORRHurt
add larger dilation rates to DDL in noise-free case on real data (ablation)traditional SFF depth extraction · LFSD, noise-freeRMSE / CORRImproved
use directional DDL G1 instead of 3x3 Laplacian (ablation)traditional SFF focus measure · HCI/LFSD/FT noise conditionsRMSE / CORRImproved
feed handcrafted DDL focus volume instead of raw focal stack or learnable focus volume (ablation)AiFDNet · HCItraining convergenceImproved
increase GRU iterations from 1 to 4 (ablation)DDL + GRU · FoDinference time per stack (s): 0.0231 -> 0.0349Hurt

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