AI Paper Atlas

Research map / Image generation / Image restoration

Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation

Xingang Pan, Xiaohang Zhan, Bo Dai, Dahua Lin, Chen Change Loy, Ping Luo

ECCV 2020 · Image generation › Image restoration · approach: Efficient restoration architectures

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 discriminator feature matching loss instead of MSE (ablation)DGP · ImageNet val 1k (colorization)ResNet50 accuracy (%): 49.1 -> 56.8Improved
use discriminator feature matching loss instead of perceptual loss (ablation)DGP · ImageNet val 1k (colorization)ResNet50 accuracy (%): 53.9 -> 56.8Improved
add progressive reconstruction to discriminator loss (ablation)DGP · ImageNet val 1k (colorization)ResNet50 accuracy (%): 56.8 -> 62.8Improved
use discriminator loss instead of MSE (ablation)DGP · ImageNet val 1k (super-resolution x4)NIQE: 6.54 -> 6.06Improved
use discriminator loss instead of perceptual loss (ablation)DGP · ImageNet val 1k (super-resolution x4)NIQE: 6.27 -> 6.06Improved
add progressive reconstruction to discriminator loss (ablation)DGP · ImageNet val 1k (super-resolution x4)NIQE: 6.06 -> 4.90Improved
use discriminator loss instead of MSE (ablation)DGP · ImageNet val 1k (super-resolution x4)PSNR: 21.24 -> 21.58Improved
add progressive reconstruction to discriminator loss (ablation)DGP · ImageNet val 1k (super-resolution x4)PSNR: 21.58 -> 22.00Improved
bias final fine-tuning toward MSE loss instead of discriminator loss (ablation)DGP · ImageNet val 1k (super-resolution x4)PSNR and NIQE: PSNR 22.00 -> 23.30, NIQE 4.90 -> 5.30Mixed
fine-tune the generator on the fly instead of fixing it (GAN inversion)BigGAN reconstruction · ImageNet val 1k (GAN inversion reconstruction)PSNR: 22.49 -> 32.89Improved
use DGP instead of DIP for inpaintinginpainting · ImageNet val 1k (inpainting)PSNR: 14.58 -> 16.97Improved
use DGP instead of DIP for adversarial defenseadversarial defense · ImageNet val 1k (adversarial defense)top-1 accuracy (%): 37.5 -> 41.3Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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