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

We propose NEMTO, the first end-to-end neural render- ing 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 illumina- tion. With 2D images of the transparent object as input, our method is capable of high-quality novel view and re- lighting synthesis. We leverage implicit Signed Distance Functions (SDF) to model the object geometry and pro- pose a refraction-aware ray bending network to model the effects of light refraction within the object. Our ray bend- ing network is more tolerant to geometric inaccuracies than traditional physically-based methods for rendering trans- parent objects. We provide extensive evaluations on both synthetic and real-world datasets to demonstrate our high- quality synthesis and the applicability of our method