Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.21491 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914110514397184 |
|---|---|
| author | Wang, Boyang Chen, Xuweiyi Gadelha, Matheus Cheng, Zezhou |
| author_facet | Wang, Boyang Chen, Xuweiyi Gadelha, Matheus Cheng, Zezhou |
| contents | Controllability, temporal coherence, and detail synthesis remain the most critical challenges in video generation. In this paper, we focus on a commonly used yet underexplored cinematic technique known as Frame In and Frame Out. Specifically, starting from image-to-video generation, users can control the objects in the image to naturally leave the scene or provide breaking new identity references to enter the scene, guided by a user-specified motion trajectory. To support this task, we introduce a new dataset that is curated semi-automatically, an efficient identity-preserving motion-controllable video Diffusion Transformer architecture, and a comprehensive evaluation protocol targeting this task. Our evaluation shows that our proposed approach significantly outperforms existing baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_21491 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Frame In-N-Out: Unbounded Controllable Image-to-Video Generation Wang, Boyang Chen, Xuweiyi Gadelha, Matheus Cheng, Zezhou Computer Vision and Pattern Recognition Controllability, temporal coherence, and detail synthesis remain the most critical challenges in video generation. In this paper, we focus on a commonly used yet underexplored cinematic technique known as Frame In and Frame Out. Specifically, starting from image-to-video generation, users can control the objects in the image to naturally leave the scene or provide breaking new identity references to enter the scene, guided by a user-specified motion trajectory. To support this task, we introduce a new dataset that is curated semi-automatically, an efficient identity-preserving motion-controllable video Diffusion Transformer architecture, and a comprehensive evaluation protocol targeting this task. Our evaluation shows that our proposed approach significantly outperforms existing baselines. |
| title | Frame In-N-Out: Unbounded Controllable Image-to-Video Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.21491 |