Abstract
Existing NeRF-based inverse rendering methods suppose that scenes are exclusively illuminated by distant light sources, neglecting the potential influence of emissive sources within a scene. In this work, we confront this limitation using LDR multi-view images captured with emissive sources turned on and off. Two key issues must be addressed: 1) ambiguity arising from the limited dynamic range along with unknown lighting details, and 2) the expensive computational cost in volume rendering to backtrace the paths leading to final object colors. We present a novel approach, ESR-NeRF, leveraging neural networks as learnable functions to represent ray-traced fields. By training networks to satisfy light transport segments, we regulate outgoing radiances, progressively identifying emissive sources while being aware of reflection areas. The results on scenes encompassing emissive sources with various properties demonstrate the superiority of ESR-NeRF in qualitative and quantitative ways. Our approach also extends its applicability to the scenes devoid of emissive sources, achieving lower CD metrics on the DTU dataset.
Abstract (translated)
现有的基于NeRF的反向渲染方法假定场景是由远距离光源独家照明，而忽略了场景内潜在的发射源影响。在本文中，我们通过开启和关闭发射源的LDR多视角图像来应对这一局限。需要解决两个关键问题：1）由于动态范围有限和未知的光线细节而产生的模糊；2）在体积渲染中，为了追溯导致最终物体颜色的路径而产生的昂贵计算成本。我们提出了ESR-NeRF，一种利用神经网络作为可学习函数来表示光迹场的全新方法。通过训练网络满足光传输段，我们调节出射辐射，在意识到反射区域的同时，逐渐确定发射源。ESR-NeRF对具有各种属性的发射源场景的性能在质量和数量上都有所改进。我们的方法还将其应用扩展到没有发射源的场景中，在DTU数据集上的CD指标较低。
URL
https://arxiv.org/abs/2404.15707
