RGB-D Neural Radiance Fields: Local Sampling for Faster Training
This work addresses training inefficiencies in 3D scene reconstruction for computer vision applications, representing an incremental improvement over existing NeRF methods.
The paper tackles the problem of slow training times and inaccurate geometry in neural radiance fields (NeRF) by introducing a depth-guided local sampling strategy and a smaller network architecture, achieving faster training without quality loss.
Learning a 3D representation of a scene has been a challenging problem for decades in computer vision. Recent advances in implicit neural representation from images using neural radiance fields(NeRF) have shown promising results. Some of the limitations of previous NeRF based methods include longer training time, and inaccurate underlying geometry. The proposed method takes advantage of RGB-D data to reduce training time by leveraging depth sensing to improve local sampling. This paper proposes a depth-guided local sampling strategy and a smaller neural network architecture to achieve faster training time without compromising quality.