AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Adaptive Noise Covariance Scheduling under Riemannian Metrics for Diffusion Models

Bolin Deng, Die Hu, Bin Tan, Jun Wu

ECCV 2026 · Image generation › Fast diffusion sampling · approach: Denoising diffusion probabilistic models · 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
replace Cholesky interpolation with BW geodesic path (fixed schedule) (ablation)BNDM · AFHQ-Cat (64x64)FID: 7.95 -> 6.40Improved
replace LE/AIRM geodesic with BW geodesic path (fixed schedule) (ablation)BNDM · AFHQ-Cat (64x64)FID: 7.95 -> 6.40Improved
use LE/AIRM geodesic instead of Cholesky interpolation (fixed schedule) (ablation)BNDM · AFHQ-Cat (64x64)FID: 7.95 -> 7.95No clear effect
add adaptive transition schedule to BW geodesic (ablation)BW+F · AFHQ-Cat (64x64)FID: 6.40 -> 6.17Improved
add adaptive transition schedule to Cholesky interpolation (ablation)CH+F · AFHQ-Cat (64x64)FID: 7.95 -> 6.43Improved
add adaptive transition schedule to LE/AIRM geodesic (ablation)LA+F · AFHQ-Cat (64x64)FID: 7.95 -> 8.36Hurt
add adaptive schedule to BW geodesic (ablation)BW+F · AFHQ-Cat (64x64)KID: 0.0034 -> 0.0034Improved
replace BNDM path and schedule with BW geodesic and adaptive scheduleBNDM · AFHQ-Cat (64x64)KID: 0.0052 -> 0.0034Improved
replace BNDM with ours at 5 sampling stepsBNDM · AFHQ-Cat (64x64), T=5FID: 82.93 -> 57.35Improved
replace BNDM with ours at 250 sampling steps on AFHQBNDM · AFHQ (64x64), T=250FID: 12.79 -> 9.51Improved
extend the method to DDIMDDIM · AFHQ-Cat (64x64)FID: 9.82 -> 6.33Improved
replace BNDM with ours for super-resolutionBNDM · AFHQ-Cat super-resolution (64 to 128)PSNR: 29.30 -> 30.01Improved

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