Neural Light Field
Neural light fields (NeLFs) represent a novel approach to 3D scene representation and rendering, aiming to improve upon the speed and efficiency limitations of neural radiance fields (NeRFs). Current research focuses on developing efficient NeLF architectures, often employing grid-based representations or light-slab approaches, and leveraging techniques like knowledge distillation and optimized network designs to achieve real-time performance, even on mobile devices. This work is significant for its potential to enable faster and more resource-efficient novel view synthesis in applications ranging from augmented reality and virtual reality to scientific visualization and robotics.
Papers
LightAvatar: Efficient Head Avatar as Dynamic Neural Light Field
Huan Wang, Feitong Tan, Ziqian Bai, Yinda Zhang, Shichen Liu, Qiangeng Xu, Menglei Chai, Anish Prabhu, Rohit Pandey, Sean Fanello, Zeng Huang, Yun Fu
Neural Light Spheres for Implicit Image Stitching and View Synthesis
Ilya Chugunov, Amogh Joshi, Kiran Murthy, Francois Bleibel, Felix Heide