Research on 3D scene graph rendering based on neural radiance fields

Abstract

Since the release of Neural Radiance Fields (NeRF), it has become the research focus of computer graphics in only three years and has become a representative method of using deep learning to deal with computer graphics tasks. The application scenarios of NeRF are very extensive, including virtual reality, augmented reality, computer graphics, 3D scene graph rendering, and other fields. However, the literatures on these aspects are not sufficient. To this end, this article introduces the basic principles of NeRF and compares and analyzes the advantages and disadvantages of NeRF and traditional graphics methods in 3D rendering tasks. According to different improvement directions, from the perspective of improving training speed, improving network generalization, and expanding to dynamic scenes, etc. Representative follow-up work based on NeRF is summarized. And the future application scenarios and development direction of NeRF are prospected.