AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

SDDM: Score-Decomposed Diffusion Models on Manifolds for Unpaired Image-to-Image Translation

Shikun Sun, Longhui Wei, Junliang Xing, Jia Jia, Qi Tian

ICML 2023 · Image generation › Fast diffusion sampling · approach: Diffusion theory and design space · 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
Replace low-pass filter manifold with BAdaIN manifold (ablation)SDDM · AFHQ Cat→DogFID: 67.56 -> 62.29Improved
Add multi-objective optimization on manifold (vs. without MOO) (ablation)SDDM · AFHQ Cat→DogPNI and FID: FID 64.93 -> 62.29; PNI 0.024 -> 0Improved
Use 16x16 chunking blocks instead of 8x8 blocks (ablation)SDDM · AFHQ Cat→DogFID and SSIM: 8x8 FID 54.56 SSIM 0.359; 16x16 FID 62.29 SSIM 0.422Mixed
Use 32x32 chunking blocks instead of 16x16 (ablation)SDDM · AFHQ Cat→DogFID and SSIM: FID 62.29 -> 68.03; SSIM 0.422 -> 0.426Mixed
Epsilon policy 1 (single manifold iteration) instead of policy 3 (ablation)SDDM · AFHQ Cat→DogFID and SSIM: FID 61.33 vs 62.29 (better); SSIM 0.413 vs 0.422 (worse)Mixed
Epsilon policy 2 (iterate twice at every step) instead of policy 3 (ablation)SDDM · AFHQ Cat→DogFID: 64.05 vs 62.29Hurt
Increase T0 manifold-stage iterations (policy 3) versus uniform single iteration (ablation)SDDM · AFHQ Cat→DogSSIM: SSIM 0.413 -> 0.422Improved
SDDM with 100 steps vs EGSDE with 1000 stepsSDDM · AFHQ Cat→DogFID: 62.29 vs 65.82 (EGSDE*, 1000 steps)Improved
SDDM vs EGSDE at 200 steps (EGSDE**)SDDM · AFHQ Cat→DogFID: 62.29 vs 70.16Improved
SDDM vs EGSDE at 1000 steps on Wild→DogSDDM · AFHQ Wild→DogFID: 57.38 vs 59.75 (FID better) but SSIM 0.328 vs 0.343 (worse)Mixed
SDDM vs EGSDE on Male→Female (1000 steps)SDDM · CelebA-HQ Male→FemaleFID: 44.37 vs 41.93 (EGSDE* better)Hurt
Use SDDM with T0=0.6T (SDDM†) instead of default T0=0.5TSDDM · AFHQ Cat→DogFID and SSIM: FID 62.29 -> 49.43; SSIM 0.422 -> 0.361Mixed

Later papers that compared with this method

4 later accepted papers report SDDM as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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