AI Paper Atlas

Research map / Image generation / Image restoration

CLDefocus: Physically Grounded Compound-Lens Defocus Blur Synthesis

Yunkyu Lee, Woohyeok Kim, Sunghyun Cho

ECCV 2026 · Image generation › Image restoration · approach: Reflection removal

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 realistic lens PSFs instead of Gaussian blur (ablation)NRKNet trained on CLDefocus · RealDOFPSNR: 22.34 -> 24.74Improved
add ISP and noise synthesis (ablation)NRKNet trained on CLDefocus · RealDOFPSNR: 23.49 -> 24.74Improved
add depth-varying layered rendering (ablation)NRKNet trained on CLDefocus · RealDOFPSNR: 24.54 -> 24.74Improved
train on CLDefocus instead of DPDDNRKNet · RealDOFPSNR: 25.03 -> 24.74 (MUSIQ 31.350 -> 35.787)Mixed
train on CLDefocus instead of DPDDNRKNet · RTFPSNR: 25.95 -> 26.62 (PSNR); LPIPS 0.207 -> 0.242Mixed
train on CLDefocus instead of SYNDOFNRKNet · RealDOFPSNR: 21.64 -> 24.74Improved
use Debye CZT instead of Rayleigh-SommerfeldPSF computation · single lens, N=256runtime (s): 45.1 -> 0.018Improved

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