The wide adoption of path‐tracing algorithms in high‐end realistic rendering has stimulated
many diverse research initiatives. In this paper we present a coherent survey of methods that …

We investigate the use of neural fields for modelling diverse mesoscale structures, such as
fur, fabric and grass. Instead of using classical graphics primitives to model the structure, we …

We present a technique for efficiently synthesizing images of atmospheric clouds using a
combination of Monte Carlo integration and neural networks. The intricacies of Lorenz-Mie …

Volume rendering under complex, dynamic lighting is challenging, especially if targeting
real-time. To address this challenge, we extend a recent direct illumination sampling …

Participating media are frequent in real-world scenes, whether they contain milk, fruit juice,
oil, or muddy water in a river or the ocean. Incoming light interacts with these participating …

Numerically solving partial differential equations (PDEs) is central to many applications in
computer graphics and scientific modeling. Conventional methods for solving PDEs often …

46: 2• Xi Deng, Shaojie Jiao, Benedikt Bitterli, and Wojciech Jarosz 1) suffer from
singularities, and 2) require at least two bounces in the medium past any surface, relegating …

Unbiased rendering of general, heterogeneous participating media currently requires using
null-collision approaches for estimating transmittance and generating free-flight distances. A …

The constellation of Earth-observing satellites continuously collects measurements of
scattered radiance, which must be transformed into geophysical parameters in order to …

The efficiency of Monte Carlo methods, commonly used to render participating media, is
directly linked to the manner in which random sampling decisions are made during path …