AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning

Ke Yu, Chao Dong, Liang Lin, Chen Change Loy

CVPR 2018 · Reinforcement learning › Visual and representation RL · approach: Scalable RL systems and environments · 222 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
use 6 rather than 12 restoration tools (ablation)RL-Restore · DIV2K test ModeratePSNR: 26.20 -> 25.72Hurt
increase toolbox size from 12 to 18 tools (ablation)RL-Restore · DIV2K test ModeratePSNR: 26.20 -> 26.17No clear effect
limit toolchain length to 2 rather than 3 (ablation)RL-Restore · DIV2K test ModeratePSNR: 26.20 -> 25.99Hurt
allow toolchain length 4 rather than 3 (ablation)RL-Restore · DIV2K test ModeratePSNR: 26.20 -> 26.20No clear effect
add slight noise and compression to tool training data (ablation)RL-Restore · DIV2K test ModeratePSNR: 25.91 -> 26.20Improved
jointly fine-tune tools using agent-selected toolchains (ablation)RL-Restore · DIV2K test ModeratePSNR: 26.20 -> 26.45Improved
replace stepwise PSNR reward with stepwise SSIM reward (ablation)RL-Restore · DIV2K test ModeratePSNR: 26.20 -> 25.20Hurt
replace stepwise PSNR reward with final PSNR reward (ablation)RL-Restore · DIV2K test ModeratePSNR: 26.20 -> 26.11No clear effect
replace stepwise PSNR reward with final MSE reward (ablation)RL-Restore · DIV2K test ModerateSSIM: 0.5441 -> 0.5166Hurt
remove the agent's stopping action (ablation)RL-Restore · DIV2K test ModeratePSNR: 26.20 -> 26.08Hurt
use the full RL-Restore toolchain instead of VDSR-sDIV2K test Severe (unseen) · DIV2K test Severe (unseen)PSNR: 24.50 -> 25.20Improved

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