Goto

Collaborating Authors

 conference


HairDiffusion: VividMulti-Colored HairEditingviaLatentDiffusion

Neural Information Processing Systems

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using textdescriptions orreference images, while preserving irrelevant attributes(e.g.,identity,background,cloth).










FullyExplicitDynamicGaussianSplatting

Neural Information Processing Systems

Meanwhile, a promising alternative, 3DGaussian Splatting (3DGS) [13], has emerged, which achieves photo-realistic rendering results with significantly faster training and rendering speeds.