SelfNeRF: Fast Training NeRF for Human from Monocular Self-rotating Video

Bo Peng     Jun Hu     Jingtao Zhou      Juyong Zhang
University of Science and Technology of China    

TL;DR: Given a monocular video of the human performer, our proposed method is able to train from scratch and converge in about twenty minutes, and then generate free-view points videos

Abstract

In this paper, we propose an efficient neural radiance field based novel view synthesis method for human performance. Given monocular self-rotating videos of human performers, our method can train from scratch and achieve high-fidelity results in about twenty minutes. Some recent works have utilized the neural radiance field for dynamic human reconstruction. However, most of these methods need multi-view inputs and require hours of training, making it still difficult for practical use. To address this challenging problem, we introduce a surface-relative representation based on multi-resolution hash encoding that can greatly improve the training speed and aggregate inter-frame information. Extensive experimental results on several different datasets demonstrate the effectiveness and efficiency of our approach to challenging monocular videos.

Method

Overview of our method. Given a sample point at any frame, we first obtain a surface-relative representation conditioned on human body surface via KNN to aggregate the corresponding point information of different frames. Then we exploit multi-resolution hash encoding to get the feature, which is the encoded input to the NeRF MLP to regress color and density.

Results

We test our method on multiple datasets (ZJU-Mocap dataset[Peng et al. 2021], People-Snapshot dataset [Alldieck et al. 2018] and our collected dataset).

Comparisons

We compare our method with state-of-the-art implicite human novel view synthesis methods.

Ablation Studies

We evaluate the choice of the human surface (SMPL or SelfRecon) in our algorithm.

Acknowledgements

This research was supported by the National Natural Science Foundation of China (No.62122071, No.62272433), and the Fundamental Research Funds for the Central Universities (No. WK3470000021).