Recent advances in Neural Radiance Fields (NeRFs) treat the problem of novel view synthesis as Sparse Radiance Field (SRF) optimization using sparse voxels for efficient and fast rendering (plenoxels,InstantNGP). In order to leverage machine learning and adoption of SRFs as a 3D representation, we present SPARF, a large-scale ShapeNet-based synthetic dataset for novel view synthesis consisting of $\sim$ 17 million images rendered from nearly 40,000 shapes at high resolution (400 X 400 pixels). The dataset is orders of magnitude larger than existing synthetic datasets for novel view synthesis and includes more than one million 3D-optimized radiance fields with multiple voxel resolutions. Furthermore, we propose a novel pipeline (SuRFNet) that learns to generate sparse voxel radiance fields from only few views. This is done by using the densely collected SPARF dataset and 3D sparse convolutions. SuRFNet employs partial SRFs from few/one images and a specialized SRF loss to learn to generate high-quality sparse voxel radiance fields that can be rendered from novel views. Our approach achieves state-of-the-art results in the task of unconstrained novel view synthesis based on few views on ShapeNet as compared to recent baselines. The SPARF dataset is made public with the code and models on the project website https://abdullahamdi.com/sparf/ .

翻译：近年来，神经辐射场（NeRF）的进展将新视角合成问题视为稀疏辐射场（SRF）优化，利用稀疏体素实现高效快速渲染（如plenoxels、InstantNGP）。为了利用机器学习并推广SRF作为三维表示，我们提出了SPARF——一个基于ShapeNet的大规模合成数据集，用于新视角合成，包含从近4万个形状渲染的约1700万张高分辨率（400×400像素）图像。该数据集比现有的新视角合成合成数据集大数个数量级，并包含超过一百万个具有多种体素分辨率的三维优化辐射场。此外，我们提出了一种新的流水线（SuRFNet），能够从仅有的少量视图学习生成稀疏体素辐射场。通过使用密集采集的SPARF数据集和三维稀疏卷积实现这一目标。SuRFNet利用来自少量/单张图像的部分SRF和专用SRF损失函数，学习生成可从新视角渲染的高质量稀疏体素辐射场。与近期基线方法相比，我们的方法在基于ShapeNet上少量视图的无约束新视角合成任务中达到了最先进水平。SPARF数据集与代码和模型已在项目网站https://abdullahamdi.com/sparf/ 上公开发布。