arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.06356cs.CVcs.AI
收藏

基于一致性调优的视频生成

Video Generation with Consistency Tuning

Chinese Academy of Sciences(中国科学院)

Chaoyi Wang, Yaozhe Song, Yafeng Zhang, Jun Pei, Lijie Xia, Jianpo Liu

AI总结:

针对长视频生成中帧存在抖动、噪声的问题,提出含四个模块的一致性调优视频生成框架,优化前后景一致性,实验证明生成质量优于现有最优方法。

摘要:

当前,各类研究都在探索长视频生成,但这类方法生成的视频帧往往存在抖动和噪声问题。为此,为生成无上述噪声的视频,我们提出了一种包含四个模块的全新框架:独立调优模块、平均融合模块、联合调优模块以及帧间一致性模块。通过依次应用我们新提出的这些模块,视频各帧中背景与前景的一致性得到了优化。此外,实验结果表明,与现有最优方法相比,我们的方法生成的视频质量更高。

英文摘要:

Currently, various studies have been exploring generation of long videos. However, the generated frames in these videos often exhibit jitter and noise. Therefore, in order to generate the videos without these noise, we propose a novel framework composed of four modules: separate tuning module, average fusion module, combined tuning module, and inter-frame consistency module. By applying our newly proposed modules subsequently, the consistency of the background and foreground in each video frames is optimized. Besides, the experimental results demonstrate that videos generated by our method exhibit a high quality in comparison of the state-of-the-art methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑