Research map / Image generation / Fast diffusion sampling
SinDiffusion: Learning a Diffusion Model From a Single Natural Image
Weilun Wang, Jianmin Bao, Wengang Zhou, Dongdong Chen, Dong Chen, Lu Yuan, Houqiang Li
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use single-scale diffusion instead of multi-scale (ablation) | SinDiffusion · Places50 subset (ablation) | SIFID: 0.74 -> 0.11 | Improved |
| use single-scale diffusion instead of multi-scale (ablation) | SinDiffusion · Places50 subset (ablation) | LPIPS diversity: 0.349 -> 0.432 | Improved |
| enlarge receptive field from 0.07 to 0.74 (ablation) | SinDiffusion · Places50 subset (ablation) | SIFID: 1.56 -> 0.08 | Improved |
| enlarge receptive field from 0.07 to 0.74 (ablation) | SinDiffusion · Places50 subset (ablation) | LPIPS diversity: 0.581 -> 0.032 | Hurt |
| enlarge receptive field from 0.36 to 0.74 (ablation) | SinDiffusion · Places50 subset (ablation) | LPIPS diversity: 0.432 -> 0.032 | Hurt |
| replace GAN-based multi-scale methods with SinDiffusion | SinDiffusion vs ConSinGAN · Places50 | LPIPS diversity: 0.305 -> 0.387 | Improved |
| replace GAN-based multi-scale methods with SinDiffusion | SinDiffusion vs ConSinGAN · Places50 | SIFID: 0.06 -> 0.06 | No clear effect |
| SinDiffusion vs ConSinGAN in paired user study | SinDiffusion · Places50 user study | preference: 81.0% | Improved |
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.
- SinGAN — SinGAN: Learning a Generative Model From a Single Natural Image (ICCV 2019) · better on 2 of 2 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
- Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation (ICML 2025 · similarity 0.89)
- Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape (ICLR 2024 · similarity 0.89)
- Patched Denoising Diffusion Models For High-Resolution Image Synthesis (ICLR 2024 · similarity 0.89)
- Neural Diffusion Models (ICML 2024 · similarity 0.88)
- Understanding the Generalization of Pretrained Diffusion Models on Out-of-Distribution Data (AAAI 2024 · similarity 0.88)
- DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization (NeurIPS 2024 · similarity 0.88)
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.
