Realistic hair rendering relies on fiber scattering models. These models are based on either ray tracing or on full wave‐propagation through the hair fiber. Ray tracing can model most of the scattering phenomenon observed but misses the important effect of diffraction. Indeed human natural hair specific dimensions and geometry demands for the wave nature of light to be taken into consideration for accurate rendering. However, current full‐wave model requires nonpratical, several days precomputation, that needs to be repeated for every change in the hair geometry or color, for appropriate results. We present in this paper a dual hair scattering model which considers the dual aspect of light: as a wave and as a ray. Our model accurately simulates both diffraction and scattering phenomena without requiring any precomputation. Furthermore, it can simulate light transport in hairs of arbitrary elliptical cross‐sections. This new dual approach enables our model to significantly improve the appearance of rendered hair and qualitatively match scattering and diffraction effects seen in photos of real hair while adding little computation overhead.
Finding a low dimensional parametric representation of measured BRDF remains challenging. Currently available solutions are either not interpretable, or rely on limited analytical solutions, or require expensive test subject based investigations. In this work, we strive to establish a parametrization space that affords the data-driven representation variance of measured BRDF models while still offering the artistic control of parametric analytical BRDFs. We present a machine learning approach that generates an interpretable disentangled parameter space. A disentangled representation is one in which each parameter is responsible for a unique generative factor and is insensitive to the ones encoded by the other parameters. To that end, we resort to a β-Variational AutoEncoder (β-VAE), a specific architecture of Deep Neural Network (DNN). After training our network, we analyze the parametrization space and interpret the learned generative factors utilizing our visual perception. It should be noted that perceptual analysis is called upon downstream of the system for interpretation purposes compared to most other existing methods where it is used upfront to elaborate the parametrization. In addition to that, we do not need a test subject investigation. A novel feature of our interpretable disentangled parametrization is the post-processing capability to incorporate new parameters along with the learned ones, thus expanding the richness of producible appearances. Furthermore, our solution allows more flexible and controllable material editing possibilities than manifold exploration. Finally, we provide a rendering interface, for real-time material editing and interpolation based on the presented new parametrization system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.