NEMTO: Neural Environment Matting for Novel View and Relighting Synthesis of Transparent Objects

arXiv:2303.11963v2 Announce Type: replace
Abstract: We propose NEMTO, the first end-to-end neural rendering pipeline to model 3D transparent objects with complex geometry and unknown indices of refraction. Commonly used appearance modeling such as the Disney BSDF model cannot accurately address this challenging problem due to the complex light paths bending through refractions and the strong dependency of surface appearance on illumination. With 2D images of the transparent object as input, our method is capable of high-quality novel view and relighting …

abstract arxiv cs.cv cs.gr disney environment geometry modeling neural rendering novel objects pipeline rendering synthesis transparent type view