Frame In-N-Out: Unbounded Controllable Image-to-Video Generation
Boyang Wang, Xuweiyi Chen, Matheus Gadelha, Zezhou Cheng
Abstract
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.
BibTeX
@inproceedings{
wang2025frame,
title={Frame In-N-Out: Unbounded Controllable Image-to-Video Generation},
author={Boyang Wang and Xuweiyi Chen and Matheus Gadelha and Zezhou Cheng},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=noiiyIk3hh}
}