Saved in:
Bibliographic Details
Main Authors: Jiang, Yudong, Xu, Baohan, Yang, Siqian, Yin, Mingyu, Liu, Jing, Xu, Chao, Wang, Siqi, Wu, Yidi, Zhu, Bingwen, Zhang, Xinwen, Zheng, Xingyu, Xu, Jixuan, Zhang, Yue, Hou, Jinlong, Sun, Huyang
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.10255
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916750541455360
author Jiang, Yudong
Xu, Baohan
Yang, Siqian
Yin, Mingyu
Liu, Jing
Xu, Chao
Wang, Siqi
Wu, Yidi
Zhu, Bingwen
Zhang, Xinwen
Zheng, Xingyu
Xu, Jixuan
Zhang, Yue
Hou, Jinlong
Sun, Huyang
author_facet Jiang, Yudong
Xu, Baohan
Yang, Siqian
Yin, Mingyu
Liu, Jing
Xu, Chao
Wang, Siqi
Wu, Yidi
Zhu, Bingwen
Zhang, Xinwen
Zheng, Xingyu
Xu, Jixuan
Zhang, Yue
Hou, Jinlong
Sun, Huyang
contents Animation has gained significant interest in the recent film and TV industry. Despite the success of advanced video generation models like Sora, Kling, and CogVideoX in generating natural videos, they lack the same effectiveness in handling animation videos. Evaluating animation video generation is also a great challenge due to its unique artist styles, violating the laws of physics and exaggerated motions. In this paper, we present a comprehensive system, AniSora, designed for animation video generation, which includes a data processing pipeline, a controllable generation model, and an evaluation benchmark. Supported by the data processing pipeline with over 10M high-quality data, the generation model incorporates a spatiotemporal mask module to facilitate key animation production functions such as image-to-video generation, frame interpolation, and localized image-guided animation. We also collect an evaluation benchmark of 948 various animation videos, with specifically developed metrics for animation video generation. Our entire project is publicly available on https://github.com/bilibili/Index-anisora/tree/main.
format Preprint
id arxiv_https___arxiv_org_abs_2412_10255
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AniSora: Exploring the Frontiers of Animation Video Generation in the Sora Era
Jiang, Yudong
Xu, Baohan
Yang, Siqian
Yin, Mingyu
Liu, Jing
Xu, Chao
Wang, Siqi
Wu, Yidi
Zhu, Bingwen
Zhang, Xinwen
Zheng, Xingyu
Xu, Jixuan
Zhang, Yue
Hou, Jinlong
Sun, Huyang
Graphics
Artificial Intelligence
Animation has gained significant interest in the recent film and TV industry. Despite the success of advanced video generation models like Sora, Kling, and CogVideoX in generating natural videos, they lack the same effectiveness in handling animation videos. Evaluating animation video generation is also a great challenge due to its unique artist styles, violating the laws of physics and exaggerated motions. In this paper, we present a comprehensive system, AniSora, designed for animation video generation, which includes a data processing pipeline, a controllable generation model, and an evaluation benchmark. Supported by the data processing pipeline with over 10M high-quality data, the generation model incorporates a spatiotemporal mask module to facilitate key animation production functions such as image-to-video generation, frame interpolation, and localized image-guided animation. We also collect an evaluation benchmark of 948 various animation videos, with specifically developed metrics for animation video generation. Our entire project is publicly available on https://github.com/bilibili/Index-anisora/tree/main.
title AniSora: Exploring the Frontiers of Animation Video Generation in the Sora Era
topic Graphics
Artificial Intelligence
url https://arxiv.org/abs/2412.10255