Knowledge Commons of Institute of Automation,CAS
MOSO: Decomposing MOtion, Scene and Object for Video Prediction | |
Sun, Mingzhen1,2; Wang, Weining1; Zhu, Xinxin1; Liu, Jing1,2 | |
2023 | |
会议名称 | IEEE/CVF Conference on Computer Vision and Pattern Recognition |
会议日期 | 2023-6-18 |
会议地点 | Vancouver, Canada |
摘要 | Motion, scene and object are three primary visual components of a video. In particular, objects represent the foreground, scenes represent the background, and motion traces their dynamics. Based on this insight, we propose a twostage MOtion, Scene and Object decomposition framework (MOSO)1 for video prediction, consisting of MOSO-VQVAE and MOSO-Transformer. In the first stage, MOSO-VQVAE decomposes a previous video clip into the motion, scene and object components, and represents them as distinct groups of discrete tokens. Then, in the second stage, MOSOTransformer predicts the object and scene tokens of the subsequent video clip based on the previous tokens and adds dynamic motion at the token level to the generated object and scene tokens. Our framework can be easily extended to unconditional video generation and video frame interpolation tasks. Experimental results demonstrate that our method achieves new state-of-the-art performance on five challenging benchmarks for video prediction and unconditional video generation: BAIR, RoboNet, KTH, KITTI and UCF101. In addition, MOSO can produce realistic videos by combining objects and scenes from different videos. |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 图像视频处理与分析 |
国重实验室规划方向分类 | 视觉信息处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/51620 |
专题 | 紫东太初大模型研究中心 |
通讯作者 | Liu, Jing |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Sun, Mingzhen,Wang, Weining,Zhu, Xinxin,et al. MOSO: Decomposing MOtion, Scene and Object for Video Prediction[C],2023. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
6704_moso_decomposin(1504KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论