HanDiffuser: Text-to-Image Generation With Realistic Hand Appearances

arXiv:2403.01693v1 Announce Type: new
Abstract: Text-to-image generative models can generate high-quality humans, but realism is lost when generating hands. Common artifacts include irregular hand poses, shapes, incorrect numbers of fingers, and physically implausible finger orientations. To generate images with realistic hands, we propose a novel diffusion-based architecture called HanDiffuser that achieves realism by injecting hand embeddings in the generative process. HanDiffuser consists of two components: a Text-to-Hand-Params diffusion model to generate SMPL-Body and MANO-Hand parameters from input text prompts, and …

abstract architecture arxiv cs.ai cs.cv diffusion generate generative generative models humans image image generation images lost novel numbers quality text text-to-image type