GNeuVox: Generalizable Neural Voxels for Fast Human Radiance Fields

1School of EIC, HUST 2Institute of AI, HUST
* denotes equal contributions.

Abstract

overview

In this paper, we propose a rendering framework that can learn moving human body structures extremely quickly from a monocular video, named as GNeuVox. The framework is built by integrating both neural fields and neural voxels. Especially, a set of generalizable neural voxels are constructed. With pretrained on various human bodies, these general voxels represent a basic skeleton and can provide strong geometric priors. For the fine-tuning process, individual voxels are constructed for learning differential textures, complementary to general voxels. Thus learning a novel body can be further accelerated, taking only a few minutes. Our method shows significantly higher training efficiency compared with previous methods, while maintaining similar rendering quality.

Video

Render Moving Human Bodies at Free Viewpoints

Render Moving Human Bodies at Any Pose

Comparison with HumanNeRF On Monocular Videos

InputHumanNeRF(288 hours) GNeuVox(Fine-tune 15 mins)


Citation

@article{gneuvox,
        title={Generalizable Neural Voxels for Fast Human Radiance Fields},
        author={Taoran Yi and Jiemin Fang and Xinggang Wang and Wenyu Liu},
        journal={arxiv:2303.15387},
        year={2023}
        }