HFNeRF: Learning Human Biomechanic Features with Neural Radiance Fields

arXiv:2404.06152v1 Announce Type: new
Abstract: In recent advancements in novel view synthesis, generalizable Neural Radiance Fields (NeRF) based methods applied to human subjects have shown remarkable results in generating novel views from few images. However, this generalization ability cannot capture the underlying structural features of the skeleton shared across all instances. Building upon this, we introduce HFNeRF: a novel generalizable human feature NeRF aimed at generating human biomechanic features using a pre-trained image encoder. While previous human NeRF methods have …

abstract arxiv cs.ai cs.cv features fields however human images instances nerf neural radiance fields novel results synthesis type view