AI Paper Atlas

Research map / Image generation / Image restoration

Latent Convolutional Models

ShahRukh Athar, Evgeny Burnaev, Victor Lempitsky

ICLR 2019 · Image generation › Image restoration · approach: Priors for restoration networks · 20 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
remove convolutional manifold constraint at test time (optimize z directly) (ablation)LCM · CelebA-HQ inpaintingMSE (inpainted pixels): 0.00171 -> 0.00854Hurt
remove convolutional manifold constraint at test time (ablation)LCM · CelebA-HQ inpaintingperceptual metric: 0.02381 -> 0.02736Hurt
remove convolutional manifold constraint at test time (ablation)LCM · CelebA-HQ inpaintingMSE (known pixels): 0.00307 -> 0.00141Hurt
remove manifold constraint at test time (ablation)LCM · CelebA and Bedroomsrestoration qualityNo clear effect
use convolutional manifold latent instead of free latent vector (LCM vs GLO)LCM · CelebA inpaintingMSE: 0.0038 -> 0.0034Improved
use convolutional manifold latent instead of free latent vector (LCM vs GLO)LCM · LSUN-Bedrooms inpaintingMSE: 0.0085 -> 0.0065Improved
LCM vs GLO on colorizationLCM · LSUN-Bedrooms colorizationMSE: 0.0075 -> 0.0066Mixed
LCM vs per-image DIP priorLCM · CelebA inpaintingMSE: 0.0091 -> 0.0034Improved
LCM vs DIP on super-resolutionLCM · CelebA super-resolutionMSE: 0.0052 -> 0.0061Hurt
LCM vs DIP on Bedrooms inpainting (user study)LCM · LSUN-Bedrooms inpaintinguser preference: 63.7% vs 29.7%Hurt
LCM vs GAN latent modelsLCM · CelebA inpaintingMSE: 0.0344 -> 0.0034Improved
add Gaussian prior on GAN latent z (ablation)WGAN/PGAN restoration · CelebA/BedroomsrealismNo clear effect

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