Research map / Image generation / Fast diffusion sampling
AlignMorph: Tuning-Free Diffusion Image Morphing via Explicit Semantic Transport
Wuyi Liu, Xu Han, Yuren Chen, Yige Mao, Zishuo Peng, Xianzhi 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 |
|---|---|---|---|
| add OT-based semantic correspondence instead of random mapping (ablation) | AlignMorph · Morph4Data | all metrics | Improved |
| add frequency-aware multiband latent transport instead of warping the entire latent (ablation) | AlignMorph · Morph4Data | all metrics | Improved |
| add bi-phase coordinate handoff instead of single coordinate frame (ablation) | AlignMorph · Morph4Data | structural coherence | Improved |
| warp key/value memories in addition to the query latent (ablation) | AlignMorph · Morph4Data | structural coherence | No clear effect |
| use FFT frequency decoupling instead of spatial average pooling (ablation) | AlignMorph · Morph4Data | generative quality | No clear effect |
| AlignMorph vs reproduced FreeMorph | AlignMorph · MorphBench | LPIPS: 85.01 -> 79.55 | Improved |
| AlignMorph vs reproduced FreeMorph | AlignMorph · MorphBench | FID: 139.79 -> 131.98 | Improved |
| AlignMorph vs reproduced FreeMorph | AlignMorph · Morph4Data | FID: 203.32 -> 188.44 | Improved |
| AlignMorph vs reproduced FreeMorph | AlignMorph · Morph4Data | PPL: 1993.42 -> 1896.30 | Improved |
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.
- FreeMorph — FreeMorph: Tuning-Free Generalized Image Morphing with Diffusion Model (ICCV 2025) · better on 9 of 9 shared results
- IMPUS — IMPUS: Image Morphing with Perceptually-Uniform Sampling Using Diffusion Models (ICLR 2024) · better on 6 of 6 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
- FreeControl: Efficient, Training-Free Structural Control via One-Step Attention Extraction (NeurIPS 2025 · similarity 0.88)
- Inversion-Free Image Editing with Language-Guided Diffusion Models (CVPR 2024 · similarity 0.88)
- Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think (NeurIPS 2025 · similarity 0.87)
- SweetDreamer: Aligning Geometric Priors in 2D diffusion for Consistent Text-to-3D (ICLR 2024 · similarity 0.87)
- Noise Diffusion for Enhancing Semantic Faithfulness in Text-to-Image Synthesis (CVPR 2025 · similarity 0.87)
- IMPUS: Image Morphing with Perceptually-Uniform Sampling Using Diffusion Models (ICLR 2024 · similarity 0.87)
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.
