3D Human Reconstruction in the Wild with Synthetic Data Using Generative Models

arXiv:2403.11111v1 Announce Type: new
Abstract: In this work, we show that synthetic data created by generative models is complementary to computer graphics (CG) rendered data for achieving remarkable generalization performance on diverse real-world scenes for 3D human pose and shape estimation (HPS). Specifically, we propose an effective approach based on recent diffusion models, termed HumanWild, which can effortlessly generate human images and corresponding 3D mesh annotations. We first collect a large-scale human-centric dataset with comprehensive annotations, e.g., text captions and …

abstract arxiv computer computer graphics cs.cv data diverse generative generative models graphics human performance show synthetic synthetic data type work world