Research map / Video / Video generation
Versatile Transition Generation with Image-to-Video Diffusion
Zuhao Yang, Jiahui Zhang, Yingchen Yu, Shijian Lu, Song Bai
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 VTG instead of DynamiCrafter | image-to-video baseline · MorphBench (Metamorphosis) | FID: 87.32 -> 67.39 | Improved |
| use VTG instead of DynamiCrafter | image-to-video baseline · MorphBench (Animation) | PPL: 11.16 -> 5.14 | Improved |
| use VTG instead of DiffMorpher | image morphing baseline · MorphBench (Metamorphosis) | PPL: 18.19 -> 22.80 | Hurt |
| use VTG instead of DiffMorpher | image morphing baseline · MorphBench (Animation) | FID: 43.15 -> 39.16 | Improved |
| use VTG instead of DiffMorpher | image morphing baseline · MorphBench (Animation) | PPL: 5.14 -> 5.14 | No clear effect |
| use VTG instead of TVG | training-free TVG · TC-Bench (Object) | TCR: 30.44 -> 33.46 | Improved |
| use VTG instead of TVG | training-free TVG · TC-Bench (Attribute) | TC-Score: 0.877 -> 0.893 | Improved |
| use VTG instead of DiffMorpher | image morphing baseline · TC-Bench (Background) | TCR: 50.00 -> 50.00 | No clear effect |
| use VTG instead of AID-I | AID attention interpolation · CIFAR-10 (concept blending) | Smoothness: 0.7861 -> 0.7932 | Improved |
| use VTG instead of AID-I | AID attention interpolation · LAION-Aesthetics (concept blending) | Smoothness: 0.8152 -> 0.8215 | Improved |
| use VTG instead of SEINE | SEINE · TC-Bench (Object) | TCR: 10.48 -> 33.46 | 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.
- SEINE — SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction (ICLR 2024) · better on 4 of 4 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
- SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction (ICLR 2024 · similarity 0.90)
- EIDT-V: Exploiting Intersections in Diffusion Trajectories for Model-Agnostic, Zero-Shot, Training-Free Text-to-Video Generation (CVPR 2025 · similarity 0.89)
- Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think (CVPR 2025 · similarity 0.88)
- Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning (NeurIPS 2024 · similarity 0.88)
- Encapsulated Composition of Text-to-Image and Text-to-Video Models for High-Quality Video Synthesis (CVPR 2025 · similarity 0.88)
- Decouple Content and Motion for Conditional Image-to-Video Generation (AAAI 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.
