AI Paper Atlas

Research map / Image generation / Super-resolution

Extreme Face Super-Resolution through Identity Fitting and Decoupling

Jiarui Yang, Hang Guo, Wen Huang, Shu-Tao Xia, Tao Dai

ECCV 2026 · Image generation › Super-resolution · approach: Perceptual and real-world SR · 0 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 personalized ID-embedding fine-tuning to the pretrained IDFSRIDFSR (PT) · CelebRef-HQ 8xPSNR: 24.29 -> 28.85Improved
add personalized ID-embedding fine-tuning to the pretrained IDFSRIDFSR (PT) · CelebRef-HQ 8xIDS: 0.3173 -> 0.2242Improved
add personalized ID-embedding fine-tuning to the pretrained IDFSRIDFSR (PT) · CelebRef-HQ 16xPSNR: 23.32 -> 24.09Improved
add personalized ID-embedding fine-tuning to the pretrained IDFSRIDFSR (PT) · CelebRef-HQ 16xIDS: 0.5227 -> 0.3625Improved
add ID embedding to the diffusion SR model (case4 removes it) (ablation)IDFSR full model · component ablation (Fig. 9)ID consistencyImproved
add style embedding to the diffusion SR model (case5 removes it) (ablation)IDFSR full model · component ablation (Fig. 9)facial attribute realismImproved
mask the LR image before concatenation (case2 vs case1 plain concatenation) (ablation)vanilla diffusion SR · component ablation (Fig. 9)perceptual qualityImproved
increase the number of reference images for ID fine-tuning from 2 to 10 (ablation)IDFSR (FT) · CelebHQ-Ref test setpixel, ID and attribute consistencyImproved
degrade the reference image progressively until reference-free (ablation)IDFSR (FT) · 16x progressive reference degradationID similarity: 0.3426 -> 0.5272Hurt
use personalized ID embedding versus DiffFace for emotion consistencyIDFSR (FT) · CelebRef-HQ 16xemotion accuracy: 67.4% -> 66.2%No clear effect

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