We present NeLF-Pro, a novel representation to model and reconstruct light fields in diverse natural scenes that vary in extent and spatial granularity. In contrast to previous fast reconstruction methods that represent the 3D scene globally, we model the light field of a scene as a set of local light field feature probes, parameterized with position and multi-channel 2D feature maps. Our central idea is to bake the scene's light field into spatially varying learnable representations and to query point features by weighted blending of probes close to the camera - allowing for mipmap representation and rendering. We introduce a novel vector-matrix-matrix (VMM) factorization technique that effectively represents the light field feature probes as products of core factors (i.e., VM) shared among local feature probes, and a basis factor (i.e., M) - efficiently encoding internal relationships and patterns within the scene. Experimentally, we demonstrate that NeLF-Pro significantly boosts the performance of feature grid-based representations, and achieves fast reconstruction with better rendering quality while maintaining compact modeling. Project webpage https://sinoyou.github.io/nelf-pro/.

翻译：我们提出NeLF-Pro——一种用于建模和重建尺度与空间粒度各异的自然场景光场的新型表征。不同于先前将三维场景整体表示的快速重建方法，我们将场景光场建模为一组局部光场特征探针，这些探针通过位置和多通道二维特征图进行参数化。核心理念在于：将场景光场烘焙至空间可变的可学习表征中，并通过加权融合相机近邻探针来查询点特征——从而支持多级纹理映射表征与渲染。我们引入了一种新颖的向量-矩阵-矩阵（VMM）分解技术，该技术可将光场特征探针有效表示为局部特征探针间共享的核心因子（即VM）与基因子（即M）的乘积形式——高效编码了场景内部关联结构与模式。实验表明，NeLF-Pro显著提升了基于特征网格表征的性能，在保持紧凑建模的同时实现了更优渲染质量下的快速重建。项目主页：https://sinoyou.github.io/nelf-pro/。