Real-Time Hair Rendering using Sequential Adversarial Networks

Lingyu Wei, Liwen Hu, Vladimir Kim, Ersin Yumer, Hao Li; Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 99-116


We present an adversarial network for rendering photorealistic hair as an alternative to conventional computer graphics pipelines. Our deep learning approach does not require low-level parameter tuning nor ad-hoc asset design. Our method simply takes a strand-based 3D hair model as input and provides intuitive user-control for color and lighting through reference images. To handle the diversity of hairstyles and its appearance complexity, we disentangle hair structure, color, and illumination properties using a sequential GAN architecture and a semi-supervised training approach. We also introduce an intermediate edge activation map to orientation field conversion step to ensure a successful CG-to-photoreal transition, while preserving the hair structures of the original input data. As we only require a feed-forward pass through the network, our rendering performs in real-time. We demonstrate the synthesis of photorealistic hair images on a wide range of intricate hairstyles and compare our technique with state-of-the-art hair rendering methods.

Related Material

author = {Wei, Lingyu and Hu, Liwen and Kim, Vladimir and Yumer, Ersin and Li, Hao},
title = {Real-Time Hair Rendering using Sequential Adversarial Networks},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
month = {September},
year = {2018}