AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

DC-Solver: Improving Predictor-Corrector Diffusion Sampler via Dynamic Compensation

Wenliang Zhao, Haolin Wang, Jie Zhou, Jiwen Lu

ECCV 2024 · Image generation › Fast diffusion sampling · approach: Fast diffusion ODE solvers · 10 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 dynamic compensation ratios to UniPC (DC-Solver) (ablation)UniPC · FFHQ unconditional NFE=5FID: 18.66 -> 10.38Improved
use constant compensation ratio 1.1 instead of dynamic ratios (ablation)DC-Solver · FFHQ NFE=5FID: 10.38 -> 13.99Hurt
use constant compensation ratio 0.9 (ablation)UniPC · FFHQ NFE=5FID: 18.66 -> 26.43Hurt
increase datapoints for ratio search from 10 to 30 (ablation)DC-Solver · FFHQ NFE=5FID: 10.38 -> 10.93No clear effect
reduce datapoints from 10 to 5 (ablation)DC-Solver · FFHQ NFE=5FID: 10.38 -> 12.39Hurt
use compensation order K=2 instead of K=1 or K=3 (ablation)DC-Solver · FFHQ NFE=5FID: 12.70 (K=1), 11.63 (K=3) -> 10.38Improved
increase optimization iterations beyond 40 (ablation)DC-Solver · FFHQ NFE=5FID: 10.38 -> 10.63No clear effect
add dynamic compensation to predictor-only DDIMDDIM · FFHQ NFE=5FID: 57.92 -> 16.56Improved
add dynamic compensation to predictor-only DPM-Solver++DPM-Solver++ · FFHQ NFE=5FID: 27.80 -> 11.97Improved
predict compensation ratios by cascade polynomial regression for unseen CFG/NFEDC-Solver · SD2.1 unseen CFG=6.0 NFE=14MSE: 0.304 -> 0.196Improved
apply DC-Solver instead of UniPC at inferenceDC-Solver · SD2.1 NFE=5inference time (s): 1.533 -> 1.532No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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