Recent years we have witnessed rapid development in NeRF-based image
rendering due to its high quality. However, point clouds rendering is somehow
less explored. Compared to NeRF-based rendering which suffers from dense
spatial sampling, point clouds rendering is naturally less computation
intensive, which enables its deployment in mobile computing device. In this
work, we focus on boosting the image quality of point clouds rendering with a
compact model design. We first analyze the adaption of the volume rendering
formulation on point clouds. Based on the analysis, we simplify the NeRF
representation to a spatial mapping function which only requires single
evaluation per pixel. Further, motivated by ray marching, we rectify the the
noisy raw point clouds to the estimated intersection between rays and surfaces
as queried coordinates, which could avoid \textit{spatial frequency collapse}
and neighbor point disturbance. Composed of rasterization, spatial mapping and
the refinement stages, our method achieves the state-of-the-art performance on
point clouds rendering, outperforming prior works by notable margins, with a
smaller model size. We obtain a PSNR of 31.74 on NeRF-Synthetic, 25.88 on
ScanNet and 30.81 on DTU. Code and data are publicly available at
this https URL

本文旨在提升点云渲染的图像质量。我们基于容积渲染公式及空间映射的分析，简化 NeRF 表示为只需每像素一次评估的空间映射函数。同时，本文还提出了用射线行进法对嘈杂的原始点云进行矫正，以避免空间频率崩溃和邻域点干扰。我们的方法在点云渲染方面取得了最先进的性能，使用更小的模型尺寸优于之前的研究，其中包括 NeRF-Synthetic（31.74），ScanNet（25.88）和 DTU（30.81）的 PSNR。