AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

SyncDiffusion: Coherent Montage via Synchronized Joint Diffusions

Yuseung Lee, Kunho Kim, Hyunjin Kim, Minhyuk Sung

NeurIPS 2023 · Image generation › Fast diffusion sampling · approach: Diffusion theory and design space · 9 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 perceptual-gradient synchronization using predicted denoised imagesMultiDiffusion joint diffusion · Text-guided panorama generation (512×3072)Intra-LPIPS: 0.69 ± 0.09 -> 0.56 ± 0.06Improved
add perceptual-gradient synchronization using predicted denoised imagesMultiDiffusion joint diffusion · Text-guided panorama generation (512×3072)Intra-Style-L: 2.98 ± 2.41 -> 1.39 ± 1.15Improved
add perceptual-gradient synchronization using predicted denoised imagesMultiDiffusion joint diffusion · Text-guided panorama generationhuman coherence preference: 33.65 -> 66.35Improved
increase gradient descent weight from 0 to 20 (ablation)SyncDiffusion · Text-guided panorama generation (512×3072)FID: 33.52 ± 12.43 -> 44.60 ± 18.45Hurt
increase gradient descent weight from 0 to 20 (ablation)SyncDiffusion · Text-guided panorama generation (512×3072)Mean-CLIP-S: 31.77 ± 2.32 -> 31.84 ± 2.19No clear effect
compute perceptual loss on noisy images rather than predicted denoised images (ablation)SyncDiffusion · Text-guided panorama generation (512×3072)Intra-LPIPS: 0.56 ± 0.06 -> 0.68 ± 0.09Hurt
use Style Loss instead of LPIPS as perceptual loss (ablation)SyncDiffusion · Text-guided panorama generation (512×3072)Intra-Style-L: 2.98 ± 2.41 -> 1.08 ± 1.10Improved
use Style Loss instead of LPIPS as perceptual loss (ablation)SyncDiffusion · Text-guided panorama generation (512×3072)FID: 33.52 ± 12.43 -> 73.05 ± 37.56Hurt
apply synchronization at 10 uniformly spaced steps rather than all 50 (ablation)SyncDiffusion · Text-guided panorama generation (512×3072)Intra-LPIPS: 0.69 ± 0.09 -> 0.62 ± 0.07Improved
apply synchronization only in the initial 3 denoising steps (ablation)SyncDiffusion · Text-guided panorama generation (512×3072)Intra-LPIPS: 0.69 ± 0.09 -> 0.62 ± 0.06Improved
apply synchronization only in the initial 3 denoising steps rather than at 10 uniform intervals (ablation)SyncDiffusion · Text-guided panorama generation (512×3072)FID: 36.22 ± 14.03 -> 35.40 ± 12.99Improved

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