AI Paper Atlas

Research map / Image generation / Image restoration

Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration

Yunjin Chen, Thomas Pock

TPAMI 2016 · Image generation › Image restoration · approach: Diffusion-based universal restoration · 1,349 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
train the influence functions in addition to filters (shared stage parameters) (ablation)TNRD 5x5 10 stages · BSD68 denoising (sigma=25, 10-stage 5x5 ablation)PSNR (dB): 28.47 -> 28.60Improved
train the influence functions in addition to filters (stage-varying parameters) (ablation)TNRD 5x5 10 stages · BSD68 denoising (sigma=25, 10-stage 5x5 ablation)PSNR (dB): 28.56 -> 28.86Improved
let parameters vary across stages (filters only) (ablation)TNRD 5x5 10 stages · BSD68 denoising (sigma=25, 10-stage 5x5 ablation)PSNR (dB): 28.47 -> 28.56Improved
let parameters vary across stages (filters and influence functions) (ablation)TNRD 5x5 10 stages · BSD68 denoising (sigma=25, 10-stage 5x5 ablation)PSNR (dB): 28.60 -> 28.86Improved
increase stages from 2 to 5 (ablation)TNRD 5x5 · BSD68 denoising (sigma=25)PSNR (dB): 28.58 -> 28.78Improved
increase stages from 5 to 8 (ablation)TNRD 5x5 · BSD68 denoising (sigma=25)PSNR (dB): 28.78 -> 28.83No clear effect
use trained TNRD instead of CSF of same capacityTNRD 5x5 5 stages · BSD68 denoising (sigma=25)PSNR (dB): 28.60 -> 28.78Improved
joint training with random initialization instead of greedy initialization (ablation)TNRD 5x5 5 stages · BSD68 denoising (sigma=25, initialization)PSNR (dB): 28.78 -> 28.61Hurt
plain initialization instead of greedy-trained initialization (ablation)TNRD 5x5 5 stages · BSD68 denoising (sigma=25, initialization)PSNR (dB): 28.78 -> 28.75No clear effect
plain initialization instead of greedy-trained initialization (ablation)TNRD 7x7 5 stages · BSD68 denoising (sigma=25)PSNR (dB): 28.92 -> 28.91No clear effect
increase filter size from 5x5 to 7x7 (ablation)TNRD 5 stages · BSD68 denoising (sigma=25)PSNR (dB): +0.14dBImproved
increase filter size from 7x7 to 9x9 (ablation)TNRD 5 stages · BSD68 denoising (sigma=25)PSNR (dB): 28.96dB, +0.05dBNo clear effect

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