AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Direct Diffusion Bridge using Data Consistency for Inverse Problems

Hyungjin Chung, Jeongsol Kim, Jong Chul Ye

NeurIPS 2023 · Image generation › Fast diffusion sampling · approach: Diffusion posterior sampling · 4 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 shallow data-consistency gradient stepsI²SB sampling · ImageNet SR×4-bicubicPSNR: 25.22 -> 26.41Improved
Add shallow data-consistency gradient stepsI²SB sampling · ImageNet SR×4-bicubicFID: 24.13 -> 19.88Improved
Add shallow data-consistency gradient stepsI²SB sampling · ImageNet deblur-gaussPSNR: 36.01 -> 37.02Improved
Add shallow data-consistency gradient stepsI²SB sampling · ImageNet deblur-uniformPSNR: 30.75 -> 31.26Improved
Use data-consistency gradient steps for JPEG restorationI²SB · ImageNet JPEG restoration QF=10PSNR: 26.12 -> 26.34Improved
Set the gradient step-size coefficient to 0.0 instead of 1.0 (ablation)CDDB · ImageNet SR×4-bicubic, 100 imagesPSNR: 26.31 -> 25.07Hurt
Increase CDDB step-size coefficient from 1.0 to 3.0 (ablation)CDDB · ImageNet SR×4-bicubic, 100 imagesPSNR: 26.31 -> 25.70Hurt
Use deeper gradients instead of shallow gradients at c=1.0 (ablation)CDDB · ImageNet SR×4-bicubic, 100 imagesPSNR: 26.31 -> 26.56Improved
Increase CDDB-deep step-size coefficient from 1.0 to 1.5 (ablation)CDDB-deep · ImageNet SR×4-bicubic, 100 imagesPSNR: 26.56 -> 26.59Improved
Increase CDDB-deep step-size coefficient from 1.0 to 3.0 (ablation)CDDB-deep · ImageNet SR×4-bicubic, 100 imagesPSNR: 26.56 -> 26.06Hurt
Apply multiple gradient-descent steps to intermediate denoised estimates (ablation)CDDB · ImageNet SR×4-bicubicPSNRImproved
Use shallow consistency gradients rather than deeper U-Net-Jacobian gradients (ablation)CDDB · Inpaintingquantitative metricsNo 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