Video Editing
Video editing research focuses on developing AI-powered methods for precise and efficient manipulation of video content, primarily driven by text or image prompts. Current efforts center on leveraging diffusion models, often adapted from image-based systems, to achieve high-quality edits while addressing challenges like temporal consistency and computational cost. This field is significant for its potential to revolutionize video production workflows, enabling both professionals and amateurs to create and modify videos with greater ease and control.
Papers
Drag-A-Video: Non-rigid Video Editing with Point-based Interaction
Yao Teng, Enze Xie, Yue Wu, Haoyu Han, Zhenguo Li, Xihui Liu
MagicStick: Controllable Video Editing via Control Handle Transformations
Yue Ma, Xiaodong Cun, Yingqing He, Chenyang Qi, Xintao Wang, Ying Shan, Xiu Li, Qifeng Chen
SAVE: Protagonist Diversification with Structure Agnostic Video Editing
Yeji Song, Wonsik Shin, Junsoo Lee, Jeesoo Kim, Nojun Kwak