AI Paper Atlas

Research map / Image generation / Editing and style transfer

Learning Warped Guidance for Blind Face Restoration

Xiaoming Li, Ming Liu, Yuting Ye, Wangmeng Zuo, Liang Lin, Ruigang Yang

ECCV 2018 · Image generation › Editing and style transfer · approach: Identity-preserving face manipulation · 161 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 WarpNet (warped guidance) instead of concatenating guide image (ablation)GFRNet · WebFace test (4x)PSNR (dB): 29.66 -> 32.31Improved
add flow loss (landmark loss and TV regularization) to WarpNet training (ablation)GFRNet · WebFace test (4x)PSNR (dB): 31.43 -> 32.31Improved
add flow loss to WarpNet training (ablation)GFRNet · VggFace2 test (4x)PSNR (dB): 26.61 -> 28.55Improved
add guided image input (ablation)GFRNet without WarpNet · VggFace2 test (4x)PSNR (dB): 25.97 -> 26.03Improved
use guided image of same identity instead of random identity (ablation)GFRNet · WebFace test (4x)PSNR (dB): 31.46 -> 32.31Improved
add flow loss when WarpNet is present vs no WarpNet (ablation)GFRNet · VggFace2 test (8x)PSNR (dB): 23.29 vs 23.17Mixed
double channels of no-WarpNet variant to match parameter count (ablation)Ours(-W) · VggFace2 test (4x)PSNR (dB): 26.03 -> 27.25Improved
add WarpNet and flow loss over parameter-matched variant (ablation)Ours(-W2) · WebFace test (4x)PSNR (dB): 29.73 -> 32.31Improved
retrain DeblurGAN on own data with guided image input (MDeblurGAN)DeblurGAN · VggFace2 test (4x)PSNR (dB): 24.65 -> 25.32Improved
retrain DnCNN on own data with guided image input (MDnCNN)DnCNN · VggFace2 test (4x)PSNR (dB): 26.73 -> 27.05Improved
retrain ARCNN on own data with guided image input (MARCNN)ARCNN · VggFace2 test (4x)PSNR (dB): 22.05 -> 25.43Improved
use GFRNet instead of retrained baselinesMDnCNN · WebFace test (4x)PSNR (dB): 29.40 -> 32.31Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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