AI Paper Atlas

Research map / Reinforcement learning / Offline RL

Beyond the Boundary: RL-Driven Solution Space Exploration for Blind Face Restoration

Bin WU, Wei Wang, Yahui Liu, Chi Zhang, Yao Zhao

ECCV 2026 · Reinforcement learning › Offline RL · approach: Behavior regularization for offline RL · 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
apply LRPO online RL post-trainingDiffBIR · CelebA-TestSSIM: 0.6775 -> 0.7021Improved
apply LRPO online RL post-trainingDiffBIR · CelebA-TestDeg.: 35.16 -> 31.19Improved
apply LRPO online RL post-trainingDiffBIR · WebPhoto-TestMUSIQ: 67.45 -> 72.71Improved
apply LRPO online RL post-trainingDiffBIR · LFW-TestCLIPIQA: 0.7296 -> 0.8073Improved
add RL (no KL) to base model (ablation)DiffBIR · CelebA-TestCLIPIQA: 0.7200 -> 0.7809Improved
add KL divergence term to RL objective (ablation)Variant 1 · CelebA-TestSSIM: 0.6849 -> 0.6750Hurt
add noise-level advantage assignment (AdA) (ablation)LRPO w/o AdA (Variant 3) · CelebA-TestSSIM: 0.6867 -> 0.7021Improved
add GT-guided likelihood regularization (ablation)LRPO w/o Reg (Variant 4) · CelebA-TestSSIM: 0.6806 -> 0.7021Improved
add RL exploration to GT-guided regularization (ablation)Reg only · CelebA-TestCLIPIQA: 0.3654 -> 0.8061Improved
use RL group exploration instead of same-reward SFT (ablation)LRPO · CelebA-TestDeg.: 36.35 -> 31.19Improved
add perceptual reward r_aq and r_fid to r_pref reward (ablation)composite reward · CelebA-TestDeg.: 36.93 -> 31.19Improved
add r_aq to r_pref + r_fid reward (ablation)composite reward · CelebA-TestCLIPIQA: 0.7355 -> 0.8061Improved

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