GHNeRF: Learning Generalizable Human Features with Efficient Neural Radiance Fields

arXiv:2404.06246v1 Announce Type: new
Abstract: Recent advances in Neural Radiance Fields (NeRF) have demonstrated promising results in 3D scene representations, including 3D human representations. However, these representations often lack crucial information on the underlying human pose and structure, which is crucial for AR/VR applications and games. In this paper, we introduce a novel approach, termed GHNeRF, designed to address these limitations by learning 2D/3D joint locations of human subjects with NeRF representation. GHNeRF uses a pre-trained 2D encoder streamlined to …

abstract advances applications arxiv cs.ai cs.cv features fields games however human information nerf neural radiance fields paper results type