UniAnimate: taming unified video diffusion models for consistent human image animation
Xiang Wang, Shiwei Zhang, Changxin Gao, Jiayu Wang, Xiaoqiang Zhou, Yingya Zhang, Luxin Yan, Nong Sang
Topics & Concepts
Computer scienceComputer visionAnimationArtificial intelligenceNoise (video)Feature (linguistics)Reference frameFrame (networking)Image (mathematics)Identity (music)Sequence (biology)Perspective (graphical)Image noiseCode (set theory)Computer animationVideo trackingImage processingVideo processingActive appearance modelKey frameState (computer science)Feature vectorMotion estimationMotion compensationMotion (physics)Pattern recognition (psychology)Computer facial animationImage restorationComputer graphics (images)Generative Adversarial Networks and Image Synthesis3D Shape Modeling and AnalysisComputer Graphics and Visualization Techniques