AAAI2023,implementation of "READ: Large-Scale Neural Scene Rendering for Autonomous Driving", the experimental results are significantly better than Nerf-based methods
It seems that the pipeline is neural rendering with classic rasterization procedure and optimization on the memory & GPU. It is great job! I am wondering if it is possible to combine with nerf idea?because it appears to be hard if doing sampling and calculating density or RGB. Is it possible to build Grid-like(sparse voxel ) structure in READ? or get some idea like block-nerf? thank u very much~~
It seems that the pipeline is neural rendering with classic rasterization procedure and optimization on the memory & GPU. It is great job! I am wondering if it is possible to combine with nerf idea?because it appears to be hard if doing sampling and calculating density or RGB. Is it possible to build Grid-like(sparse voxel ) structure in READ? or get some idea like block-nerf? thank u very much~~