AI Paper Atlas

Research map / Image generation / Super-resolution

Face Hallucination by Attentive Sequence Optimization with Reinforcement Learning

Yukai Shi, Guanbin Li, Qingxing Cao, Keze Wang, Liang Lin

TPAMI 2019 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 38 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
attend patches with the RL policy instead of enhancing the whole face (ablation)Attention-FH · LFW (x4)PSNR: +0.73 dBImproved
attend patches with the RL policy instead of enhancing the whole face (ablation)Attention-FH · LFW (x8)PSNR: +0.28 dBImproved
use RL policy instead of random patch selection (ablation)Attention-FH · LFW (x4)PSNR: 31.63 -> 33.02Improved
use RL policy instead of sequential scanning (ablation)Attention-FH · LFW (x8)PSNR: 25.98 -> 26.24Improved
use RL policy instead of spatial transformer network (ablation)Attention-FH · LFW (x4)PSNR: 28.13 -> 33.02Improved
feed restored image I_t instead of I_0 to the policy network (ablation)Attention-FH · LFW (x4)PSNR: 32.12 -> 33.02Improved
use size-free attention instead of fixed 60x60 box (ablation)Attention-FH · LFW (x4)PSNR: +0.13 dBImproved
use size-free attention instead of fixed 60x60 box (ablation)Attention-FH · LFW (x8)PSNR: +0.12 dBImproved
use random-patch recurrent enhancement instead of plain CNN-16 (ablation)Attention-FH · LFW (x4)PSNR: 29.11 -> 31.63Improved
increase recurrent steps T beyond 15 (ablation)Attention-FH · LFWPSNRNo clear effect
use PSNR-gain stabilized reward instead of absolute PSNR reward (ablation)Attention-FH · LFWPSNRImproved
use EDSR as local enhancement network (ablation)Attention-FH · LFW (x8)PSNR: 27.81 -> 28.25Improved

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