The realistic rendering of woven and knitted fabrics has posed significant challenges throughout many years. Previously, fiber-based micro-appearance models have achieved considerable success in attaining high levels of realism. However, rendering such models remains complex due to the intricate internal scatterings of hundreds or thousands of fibers within a yarn, requiring vast amounts of memory and time to render. In this paper, we introduce a novel framework to capture yarn-level appearance by tracing and aggregating many light paths through the underlying fiber geometry. We then employ lightweight neural networks to accurately model the aggregated BSDF, which allows for the precise modeling of a diverse array of materials while offering substantial improvements in speed and reductions in memory. Furthermore, we introduce a novel importance sampling scheme to further speed up the rate of convergence. We validate the efficacy and versatility of our framework through comparisons with preceding fiber-based shading models and by replicating various real-world fabrics. Our proposed model's enhanced performance and adaptability make it especially beneficial for film and video game production applications.
翻译:暂无翻译