Research map / Image generation / Editing and style transfer
Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometry
Yong-Hyun Park, Mingi Kwon, Jaewoong Choi, Junghyo Jo, Youngjung Uh
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 x-space guidance (decoder-passed basis vector) instead of direct addition x+gamma*v (ablation) | pullback latent basis editing · DDPM and Stable Diffusion editing (qualitative) | image quality / smoothness | Improved |
| edit at earlier timestep T instead of 0.6T (ablation) | pullback latent basis editing · unconditional DMs (qualitative) | edit granularity | Mixed |
| apply parallel transport of basis vector at t=0.6T instead of t=T (ablation) | pullback latent basis editing · cross-sample editing (qualitative) | semantic consistency of edits | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 2 on most shared results.
- Instruct Pix2Pix — InstructPix2Pix: Learning To Follow Image Editing Instructions (CVPR 2023) · better on 0 of 1 shared result
- SDEdit — SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations (ICLR 2022) · better on 0 of 1 shared result
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
- Hessian Geometry of Latent Space in Generative Models (ICML 2025 · similarity 0.90)
- Isometric Representation Learning for Disentangled Latent Space of Diffusion Models (ICML 2024 · similarity 0.89)
- What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion (NeurIPS 2026 · similarity 0.89)
- Diffusion Model's Generalization Can Be Characterized by Inductive Biases toward a Data-Dependent Ridge Manifold (NeurIPS 2026 · similarity 0.88)
- Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models (CVPR 2024 · similarity 0.88)
- Interpreting the Weight Space of Customized Diffusion Models (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.
