Fast and high quality neural radiance fields reconstruction based on depth regularization

Abstract

Although the Neural Radiance Fields (NeRF) has been shown to achieve high-quality novel view synthesis, existing models still perform poorly in some scenarios, particularly unbounded scenes. These models either require excessively long training times or produce suboptimal synthesis results. Consequently, we propose SD-NeRF, which consists of a compact neural radiance field model and self-supervised depth regularization. Experimental results demonstrate that SDNeRF can shorten training time by over 20 times compared to Mip-NeRF360 without compromising reconstruction accuracy.