Research map / Image generation / Editing and style transfer
A Latent Space of Stochastic Diffusion Models for Zero-Shot Image Editing and Guidance
Chen Henry Wu, Fernando De la Torre
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 stochastic-DPM latent encoding (CycleDiffusion) instead of EGSDE | AFHQ Cat to Dog · AFHQ Cat to Dog | FID: 65.82 -> 58.87 | Improved |
| CycleDiffusion versus CUT on faithfulness | AFHQ Cat to Dog · AFHQ Cat to Dog | SSIM: 0.601 -> 0.557 | Hurt |
| CycleDiffusion versus EGSDE on PSNR | AFHQ Cat to Dog · AFHQ Cat to Dog | PSNR: 19.31 -> 18.50 | Hurt |
| CycleDiffusion (stochastic latent) versus DDIB (deterministic ODE latent) | Stable Diffusion v1-4 editing · Zero-shot editing, 150 tuples (Stable Diffusion v1-4) | SD-CLIP: 0.209 -> 0.272 | Improved |
| CycleDiffusion versus DDIB on faithfulness | Stable Diffusion v1-4 editing · Zero-shot editing, 150 tuples (Stable Diffusion v1-4) | SSIM: 0.653 -> 0.731 | Improved |
| CycleDiffusion versus SDEdit on faithfulness | LDM-400M editing · Zero-shot editing, 150 tuples (LDM-400M) | SSIM: 0.390 -> 0.625 | Improved |
| add Cross Attention Control to CycleDiffusion (ablation) | CycleDiffusion · Zero-shot editing (qualitative) | structure preservation | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- SDEdit — SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations (ICLR 2022) · better on 5 of 5 shared results
- EGSDE — EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations (NeurIPS 2022) · better on 4 of 5 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
- Simpler Diffusion: 1.5 FID on ImageNet512 with Pixel-space Diffusion (CVPR 2025 · similarity 0.90)
- Denoising Diffusion Bridge Models (ICLR 2024 · similarity 0.90)
- Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models (CVPR 2024 · similarity 0.90)
- High-Fidelity Diffusion-Based Image Editing (AAAI 2024 · similarity 0.90)
- An Edit Friendly DDPM Noise Space: Inversion and Manipulations (CVPR 2024 · similarity 0.90)
- Unsupervised Region-Based Image Editing of Denoising Diffusion Models (AAAI 2025 · similarity 0.89)
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.
