Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2407.06358 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929414371016704 |
|---|---|
| author | Ju, Xuan Gao, Yiming Zhang, Zhaoyang Yuan, Ziyang Wang, Xintao Zeng, Ailing Xiong, Yu Xu, Qiang Shan, Ying |
| author_facet | Ju, Xuan Gao, Yiming Zhang, Zhaoyang Yuan, Ziyang Wang, Xintao Zeng, Ailing Xiong, Yu Xu, Qiang Shan, Ying |
| contents | Sora's high-motion intensity and long consistent videos have significantly impacted the field of video generation, attracting unprecedented attention. However, existing publicly available datasets are inadequate for generating Sora-like videos, as they mainly contain short videos with low motion intensity and brief captions. To address these issues, we propose MiraData, a high-quality video dataset that surpasses previous ones in video duration, caption detail, motion strength, and visual quality. We curate MiraData from diverse, manually selected sources and meticulously process the data to obtain semantically consistent clips. GPT-4V is employed to annotate structured captions, providing detailed descriptions from four different perspectives along with a summarized dense caption. To better assess temporal consistency and motion intensity in video generation, we introduce MiraBench, which enhances existing benchmarks by adding 3D consistency and tracking-based motion strength metrics. MiraBench includes 150 evaluation prompts and 17 metrics covering temporal consistency, motion strength, 3D consistency, visual quality, text-video alignment, and distribution similarity. To demonstrate the utility and effectiveness of MiraData, we conduct experiments using our DiT-based video generation model, MiraDiT. The experimental results on MiraBench demonstrate the superiority of MiraData, especially in motion strength. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_06358 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions Ju, Xuan Gao, Yiming Zhang, Zhaoyang Yuan, Ziyang Wang, Xintao Zeng, Ailing Xiong, Yu Xu, Qiang Shan, Ying Computer Vision and Pattern Recognition Sora's high-motion intensity and long consistent videos have significantly impacted the field of video generation, attracting unprecedented attention. However, existing publicly available datasets are inadequate for generating Sora-like videos, as they mainly contain short videos with low motion intensity and brief captions. To address these issues, we propose MiraData, a high-quality video dataset that surpasses previous ones in video duration, caption detail, motion strength, and visual quality. We curate MiraData from diverse, manually selected sources and meticulously process the data to obtain semantically consistent clips. GPT-4V is employed to annotate structured captions, providing detailed descriptions from four different perspectives along with a summarized dense caption. To better assess temporal consistency and motion intensity in video generation, we introduce MiraBench, which enhances existing benchmarks by adding 3D consistency and tracking-based motion strength metrics. MiraBench includes 150 evaluation prompts and 17 metrics covering temporal consistency, motion strength, 3D consistency, visual quality, text-video alignment, and distribution similarity. To demonstrate the utility and effectiveness of MiraData, we conduct experiments using our DiT-based video generation model, MiraDiT. The experimental results on MiraBench demonstrate the superiority of MiraData, especially in motion strength. |
| title | MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.06358 |