Real-time Neural Woven Fabric Rendering

TL;DR

This paper introduces a lightweight neural network for real-time rendering of woven fabrics, achieving high-quality visuals at nearly 60 fps by efficiently encoding fabric patterns and parameters.

Contribution

It presents a novel neural network approach that encodes diverse woven fabrics at multiple scales with a small latent vector, enabling fast and high-quality real-time rendering.

Findings

Achieves nearly 60 fps rendering on RTX 3090.

Produces high-quality, aliasing-free woven fabric visuals.

Supports editing of fabric patterns in real time.

Abstract

Woven fabrics are widely used in applications of realistic rendering, where real-time capability is also essential. However, rendering realistic woven fabrics in real time is challenging due to their complex structure and optical appearance, which cause aliasing and noise without many samples. The core of this issue is a multi-scale representation of the fabric shading model, which allows for a fast range query. Some previous neural methods deal with the issue at the cost of training on each material, which limits their practicality. In this paper, we propose a lightweight neural network to represent different types of woven fabrics at different scales. Thanks to the regularity and repetitiveness of woven fabric patterns, our network can encode fabric patterns and parameters as a small latent vector, which is later interpreted by a small decoder, enabling the representation of different types of fabrics. By applying the pixel's footprint as input, our network achieves multi-scale representation. Moreover, our network is fast and occupies little storage because of its lightweight structure. As a result, our method achieves rendering and editing woven fabrics at nearly 60 frames per second on an RTX 3090, showing a quality close to the ground truth and being free from visible aliasing and noise.