2 papers
cs.CV2024
Consistent Human Image and Video Generation with Spatially Conditioned Diffusion
Mingdeng Cao, Chong Mou, Ziyang Yuan +4
Consistent human-centric image and video synthesis aims to generate images or videos with new poses while preserving appearance consistency with a given reference image, which is c…
cs.CV2024
Instruction-based Image Manipulation by Watching How Things Move
Mingdeng Cao, Xuaner Zhang, Yinqiang Zheng +1
This paper introduces a novel dataset construction pipeline that samples pairs of frames from videos and uses multimodal large language models (MLLMs) to generate editing instructi…