FLATTEN: Optical FLow-guided ATTENtion for Consistent Text-to-video EditingCong Yang, Ming Xu,Christian Simon,Shoufa Chen, Jianxin Ren, Yi Xie,Juan-Manuel Pérez-Rúa,Bodo Rosenhahn,Tao Xiang,Sen HearXiv (Cornell University)（2023）引用 67|浏览2关键词User Attention Model,Image InpaintingAI 理解论文溯源树样例生成溯源树，研究论文发展脉络Chat Paper正在生成论文摘要
