Showing cs.CVShow all
3 papers · 1 filter
cs.CV2024
HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation
Zhenzhi Wang, Yixuan Li, Yanhong Zeng +8
Human image animation involves generating videos from a character photo, allowing user control and unlocking the potential for video and movie production. While recent approaches y…
cs.CV2024
A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting
Junhao Zhuang, Yanhong Zeng, Wenran Liu +2
Advancing image inpainting is challenging as it requires filling user-specified regions for various intents, such as background filling and object synthesis. Existing approaches fo…
cs.CV2024
Live2Diff: Live Stream Translation via Uni-directional Attention in Video Diffusion Models
Zhening Xing, Gereon Fox, Yanhong Zeng +4
Large Language Models have shown remarkable efficacy in generating streaming data such as text and audio, thanks to their temporally uni-directional attention mechanism, which mode…