Neural radiance fields, or NeRFs, have become the de facto approach for high-quality view synthesis from a collection of images captured from multiple viewpoints. However, many issues remain when capturing images in-the-wild under challenging conditions, such as low light, high dynamic range, or rapid motion leading to smeared reconstructions with noticeable artifacts. In this work, we introduce quanta radiance fields, a novel class of neural radiance fields that are trained at the granularity of individual photons using single-photon cameras (SPCs). We develop theory and practical computational techniques for building radiance fields and estimating dense camera poses from unconventional, stochastic, and high-speed binary frame sequences captured by SPCs. We demonstrate, both via simulations and a SPC hardware prototype, high-fidelity reconstructions under high-speed motion, in low light, and for extreme dynamic range settings.

翻译：神经辐射场（NeRF）已成为从多视角采集的图像集合中进行高质量视图合成的实际标准方法。然而，在具有挑战性的条件下（如低光照、高动态范围或快速运动导致重建结果模糊并伴有明显伪影）进行野外图像采集时，许多问题仍然存在。在本工作中，我们引入了量子辐射场，这是一类新型的神经辐射场，其利用单光子相机（SPC）在单个光子的粒度上进行训练。我们发展了从SPC捕获的非传统、随机且高速的二进制帧序列构建辐射场并估计密集相机位姿的理论与实用计算技术。我们通过仿真和SPC硬件原型验证了该方法在高速运动、低光照及极端动态范围设置下均能实现高保真重建。