AI Paper Atlas

Research map / Image generation / Super-resolution

Super-Identity Convolutional Neural Network for Face Hallucination

Kaipeng Zhang, Zhanpeng Zhang, Chia-Wen Cheng, Winston H. Hsu, Yu Qiao, Wei Liu, Tong Zhang

ECCV 2018 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 160 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 super-identity loss (alpha 0 -> 8) (ablation)SICNN · Set C (12x14 -> 96x112, 8x)identity similarity: 0.4418 -> 0.5978Improved
add super-identity loss (alpha 0 -> 8) (ablation)SICNN · LFWaccuracy: 97.61% -> 98.25%Improved
add super-identity loss (alpha 0 -> 8) (ablation)SICNN · YTFaccuracy: 93.20% -> 93.82%Improved
increase alpha from 8 to 32 (ablation)SICNN · LFWaccuracy: 98.25% -> 98.16%No clear effect
use domain-integrated training instead of joint training from scratch (approach I) (ablation)SICNN · Set C (12x14 -> 96x112, 8x)identity similarity: 0.3875 -> 0.5978Improved
use domain-integrated training instead of fixed HR-trained recognizer (approach II) (ablation)SICNN · Set C (12x14 -> 96x112, 8x)identity similarity: 0.4829 -> 0.5978Improved
use domain-integrated training instead of one-shot alternating training (approach III) (ablation)SICNN · Set C (12x14 -> 96x112, 8x)identity similarity: 0.5132 -> 0.5978Improved
use domain-integrated training instead of approach III (ablation)SICNN · LFWaccuracy: 97.58% -> 98.25%Improved
add perceptual loss from recognition net to UR-DGN (UR-DGN*)UR-DGN · Set C (12x14 -> 96x112, 8x)identity similarity: 0.3682 -> 0.5267Improved
SICNN versus UR-DGN* (adding super-identity loss with DI training)UR-DGN* · Set C (12x14 -> 96x112, 8x)identity similarity: 0.5267 -> 0.5978Improved
use adversarial loss (UR-DGN) instead of L2 only (LapSRN)LapSRN · Set C (12x14 -> 96x112, 8x)identity similarity: 0.4361 -> 0.3682Hurt
use SICNN instead of LapSRNLapSRN · Set C (12x14 -> 96x112, 8x)PSNR (dB): 26.1451 -> 26.8945Improved

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