Recent advances in image editing have enabled fine-grained and highly controllable visual modifications. However, achieving similar levels of controllability in video editing remains an open challenge, particularly for precise local edits, dynamic temporal effects, and consistent lighting across frames.In this paper, w...
Guo-Jun Lei, Hong Li, Hong-Bing Yang et al.· 0 citations
A pixel-pair temporal warped flow field is developed that can directly generate corresponding video editing samples in real time from image editing samples, and it is demonstrated across multiple levels of video editing tasks that a model can learn video editing using only such data.
In line with the prevailing direction of vision research, we explore the integration of both generation and editing capabilities for video and image modalities within a single model. Current approaches to collecting video editing data typically depend on labour-intensive, time-consuming curated procedures--involving ob...