Neural Microfacet Fields for Inverse Rendering
This work addresses the challenge of inverse rendering for computer vision and graphics applications, offering an incremental improvement by integrating surface-based light transport with recent volume rendering techniques.
The paper tackles the problem of recovering materials, geometry, and environment illumination from images by introducing Neural Microfacet Fields, which combines microfacet reflectance models with volumetric rendering to achieve high fidelity results in inverse rendering and competitive novel view synthesis.
We present Neural Microfacet Fields, a method for recovering materials, geometry, and environment illumination from images of a scene. Our method uses a microfacet reflectance model within a volumetric setting by treating each sample along the ray as a (potentially non-opaque) surface. Using surface-based Monte Carlo rendering in a volumetric setting enables our method to perform inverse rendering efficiently by combining decades of research in surface-based light transport with recent advances in volume rendering for view synthesis. Our approach outperforms prior work in inverse rendering, capturing high fidelity geometry and high frequency illumination details; its novel view synthesis results are on par with state-of-the-art methods that do not recover illumination or materials.