AI Paper Atlas

Research map / Image generation / Image restoration

Deep Self-Dissimilarities as Powerful Visual Fingerprints

Idan Kligvasser, Tamar Rott Shaham, Yuval Bahat, Tomer Michaeli

NeurIPS 2021 · Image generation › Image restoration · approach: Priors for restoration networks · 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
Use deeper VGG layers (ReLU51 vs ReLU21) for DSD2 full-referenceLDSD2 · PieAPPPearson correlation: 0.463 -> 0.761Improved
Use alpha=4 instead of alpha=2 in DSD full-reference measureLDSD · PieAPP, ReLU41Pearson correlation: 0.769 -> 0.607Hurt
DSD instead of style lossFull-reference measure · PieAPP, ReLU41Pearson correlation: 0.711 -> 0.769Improved
DSD instead of style loss at shallow layerFull-reference measure · PieAPP, ReLU21Pearson correlation: 0.645 -> 0.463Hurt
Multi-scale style loss instead of single-scale style (ablation)Style loss · PieAPP, ReLU31Pearson correlation: 0.714 -> 0.698Hurt
Use alpha=4 instead of alpha=2 in no-reference measureQDSD · PieAPP no-referencePearson correlation: 0.330 -> 0.444Improved
DSD4 no-reference vs BRISQUEQDSD4 · PieAPP no-referencePearson correlation: 0.363 -> 0.444Improved
Stop DSD minimization at 500 iterations instead of 5KImage DSD optimization · ESRGAN outputDSD value / visual quality: 2.2 · 10−3 vs 1.2 · 10−3Mixed
Replace CX loss with DSD loss (ablation)xSRResNet 5 blocks · DIV2K 4x SR, ReLU21NIQE: 7.87 -> 3.49Improved
Replace Style loss with DSD loss (ablation)xSRResNet 5 blocks · DIV2K 4x SR, ReLU21NIQE: 3.64 -> 3.49Improved
Replace Style loss with DSD loss (ablation)xSRResNet 5 blocks · DIV2K 4x SR, ReLU31NIQE: 4.20 -> 4.06Improved
Replace PDL with DSD loss (ablation)xSRResNet 5 blocks · DIV2K 4x SR, ReLU22NIQE: 4.33 -> 3.78Improved

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