论文标题
通过辐射映射呈现呈现云的增强点云
Boosting Point Clouds Rendering via Radiance Mapping
论文作者
论文摘要
近年来，由于其高质量，我们目睹了基于NERF的图像渲染的快速发展。但是，点云渲染的探索程度较低。与基于NERF的渲染相比，具有密集的空间采样，Point Clouds渲染自然较少计算密集型，从而使其在移动计算设备中的部署。在这项工作中，我们专注于通过紧凑的模型设计提高点云的图像质量。我们首先分析了点云上体积渲染公式的适应。基于分析，我们将NERF表示形式简化为空间映射函数，该空间映射函数仅需要每个像素单一评估。此外，由于查询坐标，我们以射线行进为动机，将嘈杂的原始点云纠正为射线和表面之间的估计相交，这可以避免\ textit {空间频率崩溃}和邻居点干扰。我们的方法由栅格化，空间映射和改进阶段组成，在点云渲染上实现了最先进的性能，超过了较小的模型大小的显着边缘的先前作品。我们在NERF合成器上获得31.74的PSNR，在扫描仪上获得25.88，在DTU上获得30.81。代码和数据可在https://github.com/seanywang0408/radiancemapping上公开获取。
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 https://github.com/seanywang0408/RadianceMapping.
