flâneur

Point-NeRF: Point-based Neural Radiance Fields

xharlie.github.io · 769 words · saved by 1 readers

Volumetric neural rendering methods like NeRF generate high-quality view synthesis results but are optimized per-scene leading to prohibitive reconstruction time. On the other hand, deep multi-view stereo methods can quickly reconstruct scene geometry via direct network inference. Point-NeRF combines the advantages of these two approaches by using neural 3D point clouds, with associated neural features, to model a radiance field. Point-NeRF can be rendered efficiently by aggregating neural point features near scene surfaces, in a ray marching-based rendering pipeline. Moreover, Point-NeRF can be initialized via direct inference of a pre-trained deep network to produce a neural point cloud; this point cloud can be finetuned to surpass the visual quality of NeRF with 30X faster training time. Point-NeRF can be combined with other 3D reconstruction methods and handles the errors and outliers in such methods via a novel pruning and growing mechanism. Overview of Point-NeRF. (a) From multi-

Point-NeRF: Point-based Neural Radiance Fields --> Visitors: Point-NeRF: Point-based Neural Radiance Fields (CVPR 2022 Oral 🤩🤯🔥) A high performance novel neural radiance representation. Qiangeng Xu , Zexiang Xu , Julien Philip , Sai Bi , Zhixin Shu Kalyan Sunkavalli , Ulrich Neumann Paper Code Oral Presentation @ CVPR 2022 Abstract Volumetric neural rendering methods like NeRF generate high-quality view synthesis results but are optimized per-scene leading to prohibitive reconstruction time. On the other hand, deep multi-view stereo methods can quickly reconstruct scene geometry via direct

related reading