Neural Hair Rendering
This addresses the challenge of realistic hair rendering in computer graphics, offering a more flexible solution for applications like virtual characters or animations, though it is incremental as it builds on unsupervised image translation methods.
The paper tackles the problem of generating photo-realistic images from 3D hair models without requiring supervised data, achieving realistic renderings through an unsupervised pipeline that handles arbitrary models.
In this paper, we propose a generic neural-based hair rendering pipeline that can synthesize photo-realistic images from virtual 3D hair models. Unlike existing supervised translation methods that require model-level similarity to preserve consistent structure representation for both real images and fake renderings, our method adopts an unsupervised solution to work on arbitrary hair models. The key component of our method is a shared latent space to encode appearance-invariant structure information of both domains, which generates realistic renderings conditioned by extra appearance inputs. This is achieved by domain-specific pre-disentangled structure representation, partially shared domain encoder layers and a structure discriminator. We also propose a simple yet effective temporal conditioning method to enforce consistency for video sequence generation. We demonstrate the superiority of our method by testing it on a large number of portraits and comparing it with alternative baselines and state-of-the-art unsupervised image translation methods.