3 papers
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…
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…
eess.IV2024
Sagiri: Low Dynamic Range Image Enhancement with Generative Diffusion Prior
Baiang Li, Sizhuo Ma, Yanhong Zeng +5
Capturing High Dynamic Range (HDR) scenery using 8-bit cameras often suffers from over-/underexposure, loss of fine details due to low bit-depth compression, skewed color distribut…