PEEKABOO: Interactive Video Generation via Masked-Diffusion
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909175990190080 |
|---|---|
| author | Jain, Yash Nasery, Anshul Vineet, Vibhav Behl, Harkirat |
| author_facet | Jain, Yash Nasery, Anshul Vineet, Vibhav Behl, Harkirat |
| contents | Modern video generation models like Sora have achieved remarkable success in producing high-quality videos. However, a significant limitation is their inability to offer interactive control to users, a feature that promises to open up unprecedented applications and creativity. In this work, we introduce the first solution to equip diffusion-based video generation models with spatio-temporal control. We present Peekaboo, a novel masked attention module, which seamlessly integrates with current video generation models offering control without the need for additional training or inference overhead. To facilitate future research, we also introduce a comprehensive benchmark for interactive video generation. This benchmark offers a standardized framework for the community to assess the efficacy of emerging interactive video generation models. Our extensive qualitative and quantitative assessments reveal that Peekaboo achieves up to a 3.8x improvement in mIoU over baseline models, all while maintaining the same latency. Code and benchmark are available on the webpage. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_07509 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | PEEKABOO: Interactive Video Generation via Masked-Diffusion Jain, Yash Nasery, Anshul Vineet, Vibhav Behl, Harkirat Computer Vision and Pattern Recognition Machine Learning Modern video generation models like Sora have achieved remarkable success in producing high-quality videos. However, a significant limitation is their inability to offer interactive control to users, a feature that promises to open up unprecedented applications and creativity. In this work, we introduce the first solution to equip diffusion-based video generation models with spatio-temporal control. We present Peekaboo, a novel masked attention module, which seamlessly integrates with current video generation models offering control without the need for additional training or inference overhead. To facilitate future research, we also introduce a comprehensive benchmark for interactive video generation. This benchmark offers a standardized framework for the community to assess the efficacy of emerging interactive video generation models. Our extensive qualitative and quantitative assessments reveal that Peekaboo achieves up to a 3.8x improvement in mIoU over baseline models, all while maintaining the same latency. Code and benchmark are available on the webpage. |
| title | PEEKABOO: Interactive Video Generation via Masked-Diffusion |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2312.07509 |