Rendering realistic appearances of homogeneous translucent materials, such as milk and marble, poses challenges due to the complexity of subsurface scattering. In this paper, we present a neural method for real-time rendering of homogeneous translucent objects. Based on the observation that light propagation inside a highly scattered media is like a diffusion process (Stam 1995), we propose a neural data structure named diffusion block to mimic the behavior of the diffusion process. The diffusion block is built upon a recent network structure named DiffusionNet (Sharp et al. 2022) with a few modifications to adapt to our problem of translucent rendering. Our network is lightweight and efficient, leading to a real-time rendering method. Furthermore, our method supports dynamic material properties and diverse lighting conditions. Comparisons with state-of-the-art real-time translucent rendering methods demonstrate the superiority of our method in rendering quality.

A key advantage of vector graphics over raster graphics is their editability. For example, linear gradients define a spatially varying color fill with a few intuitive parameters, which are ubiquitously supported in standard vector graphics formats and libraries. By layering regions filled with linear gradients, complex appearances can be created. We propose an automatic method to convert a raster image into layered regions of linear gradients. Given an input raster image segmented into regions, our approach decomposes the resulting regions into opaque and semi-transparent linear gradient fills. Our approach is fully automatic (e.g., users do not identify a background as in previous approaches) and exhaustively considers all possible decompositions that satisfy perceptual cues. Experiments on a variety of images demonstrate that our method is robust and effective.