AI Paper Atlas

Research map / Image generation / Super-resolution

Deep Decomposition Learning for Inverse Imaging Problems

Dongdong Chen, Mike E. Davies

ECCV 2020 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 39 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 range-space projector Pr to DDN (versus none) (ablation)DDN · Set5 SR x2 (sigma=0.1, BSDS300 train)PSNR (dB): 22.31 -> 25.82Improved
add null-space projector Pn to DDN (versus none) (ablation)DDN · Set5 SR x2 (sigma=0.1, BSDS300 train)PSNR (dB): 22.31 -> 20.95 for Pn aloneImproved
add Pn on top of Pr (ablation)DDN · Set5 SR x2 (sigma=0.1, BSDS300 train)PSNR (dB): 25.82 -> 26.30Improved
add Pr on top of Pn (ablation)DDN · Set5 SR x2 (sigma=0.1, BSDS300 train)PSNR (dB): 20.95 -> 26.30Improved
add Pr and Pn physics to residual learning (DDN1) in generalization (ablation)DDN · Set5 SR x2 (sigma=0.1, BSDS300 train)generalization error x10^-3: 1.75 -> 1.26Mixed
use cascade instead of independent connection (ablation)DDN · Set5 SR x2 (sigma=0.1, BSDS300 train)PSNR (dB): 26.15 -> 26.30Improved
use decoupled instead of joint training in cascade DDN (ablation)DDN · Set5 SR x2 (sigma=0.1, BSDS300 train)PSNR (dB): 26.30 -> 26.38No clear effect
use DDN instead of ResUnetCS-MRF · CS-MRF X reconstruction (N=10)NMSE x10^-2: 1.119 -> 1.056Improved
use DDN instead of NPGD with few samplesCS-MRF · CS-MRF X reconstruction (N=10)NMSE x10^-2: 1.689 -> 1.056Improved
use DDN instead of NSNCS-MRF · CS-MRF T1 map (N=100)PSNR (dB): 18.49 -> 18.92Improved
use DDN instead of NSNCS-MRF · CS-MRF T1 map (N=10)PSNR (dB): 15.25 -> 15.90Improved
use DDN instead of NPGD for inference costCS-MRF · CS-MRF reconstructioninference time (sec): 0.15 -> 0.06Improved

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