物体光场的无监督发现与组合
Unsupervised Discovery and Composition of Object Light Fields
AI总结：
针对以物体为中心的神经场景表示中逐物体光线步进成本高、采样不足的问题，提出COLF将物体表示为光场并通过光场组合器重建全局光场，实现无监督分解、SOTA重建与新视角合成，且训练和渲染速度提升数个数量级。
摘要：
连续和离散的神经场景表示最近已成为3D场景理解的一种强大新范式。近期研究致力于解决以物体为中心的神经场景表示的无监督发现问题。然而，光线步进（ray-marching）成本高昂，且每个物体表示都必须单独进行光线步进，使这一问题进一步加剧，导致辐射场采样不足，进而在训练和渲染过程中产生带噪声的渲染结果、较低的帧率以及很高的内存和时间复杂度。本文提出在以物体为中心的组合式场景表示中将物体表示为光场。我们提出了一个新颖的光场组合器模块，能够从一组以物体为中心的光场重建全局光场。我们的方法名为 Compositional Object Light Fields（COLF，组合式物体光场），能够无监督地学习以物体为中心的神经场景表示，在标准数据集上取得最先进的重建和新视角合成性能，并且渲染和训练速度比现有3D方法快数个数量级。
英文摘要：
Neural scene representations, both continuous and discrete, have recently emerged as a powerful new paradigm for 3D scene understanding. Recent efforts have tackled unsupervised discovery of object-centric neural scene representations. However, the high cost of ray-marching, exacerbated by the fact that each object representation has to be ray-marched separately, leads to insufficiently sampled radiance fields and thus, noisy renderings, poor framerates, and high memory and time complexity during training and rendering. Here, we propose to represent objects in an object-centric, compositional scene representation as light fields. We propose a novel light field compositor module that enables reconstructing the global light field from a set of object-centric light fields. Dubbed Compositional Object Light Fields (COLF), our method enables unsupervised learning of object-centric neural scene representations, state-of-the-art reconstruction and novel view synthesis performance on standard datasets, and rendering and training speeds at orders of magnitude faster than existing 3D approaches.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
