SelfNeRF: Fast Training NeRF for Human from Monocular Self-rotating Video
This addresses the problem of slow and multi-view-dependent human reconstruction for practical applications, though it is incremental over existing NeRF methods.
The paper tackles fast neural radiance field training for human novel view synthesis from monocular self-rotating videos, achieving high-fidelity results in about twenty minutes.
In this paper, we propose SelfNeRF, an efficient neural radiance field based novel view synthesis method for human performance. Given monocular self-rotating videos of human performers, SelfNeRF 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 SelfNeRF to challenging monocular videos.