While hair is an essential component of virtual humans, it is also one of the most challenging digital assets to create. Existing automatic techniques lack the generality and flexibility to create rich hair variations, while manual authoring interfaces often require considerable artistic skills and e↵orts, especially for intricate 3D hair structures that can be dicult to navigate. We propose an interactive hair modeling system that can help create complex hairstyles in minutes or hours that would otherwise take much longer with existing tools. Modelers, including novice users, can focus on the overall hairstyles and local hair deformations, as our system intelligently suggests the desired hair parts.

Our method combines the flexibility of manual authoring and the convenience of data-driven automation. Since hair contains intricate 3D structures such as buns, knots, and strands, they are inherently challenging to create using traditional 2D interfaces. Our system provides a new 3D hair authoring interface for immersive interaction in virtual reality (VR). Users can draw high-level guide strips, from which our system predicts the most plausible hairstyles via a deep neural network trained from a professionally curated dataset.

Each hairstyle in our dataset is composed of multiple variations, serving as blend-shapes to fit the user drawings via global blending and local deformation. The fitted hair models are visualized as interactive suggestions that the user can select, modify, or ignore. We conducted a user study to confirm that our system can significantly reduce manual labor while improve the output quality for modeling a variety of head and facial hairstyles that are challenging to create via existing techniques.

We represent our hair models as textured polygonal strips, which are widely adopted in AAA real-time games such as Final Fantasy 15 and Uncharted 4, and state-of-theart real-time performance-driven CG characters such as the “Siren” demo shown at GDC 2018 [35]. Hairstrips are flexible to model and highly ecient to render [25], suitable for authoring, animating, and rendering multiple virtual characters. The resulting strip-based hair models can be also converted to other formats such as strands. In contrast, with strand-based models, barely a single character could be rendered on a high-end machine, and existing approaches for converting strands into poly-strips tend to cause adverse rendering e↵ects due to the lack of consideration of appearances and textures during optimization.

To connect imprecise manual interactions with detailed hairstyles, we design a deep neural network architecture to classify sparse and varying number of input strokes to a matching hairstyle in a database. We first ask hair modeling artists to manually create a strip-based hair database with diverse styles and structures. We then expand our initial hair database using non-rigid deformations so that the deformed hair models share the same topology (e.g. ponytail) but vary in lengths and shapes. To simulate realistic usage scenarios, we train the network using varying numbers of sparse representative strokes. To amplify the training power of the limited data set and to enhance robustness of classification, the network maps pairs instead of individual strips into a latent feature space. The mapping stage has shared parameter layers and max-pooling, ensuring our network scales well to arbitrary numbers of user strokes.

We first resolve the strip-head collision. To accelerate the computation, we pre-compute a dense volumetric levelset field with respect to the scalp surface. For each grid cell, its direction and distance to the scalp are also precomputed and stored. During run time, samples inside the head are detected and projected back to their nearest points on the scalp, and samples outside the head remain fixed.

With the calculated sample locations, we proceed to reconstruct the full geometry of hair details. In particular, we build the Bishop frame [5] for each strip, and use the parallel transport method to calculate the transformation at each sample point. The full output hair mesh could be easily transformed via linear blending of these sample transformations.

We show how our system can help author high-quality hair models with large variations. Figure 11 shows the modeling results created with very sparse set of guide strips. We first validate the performance of hairstyle prediction. As seen from the first and second column, our prediction network is capable of capturing high-level features of input strips, such as hair length and curliness. We then present the e↵ect of blending and deformation in fitting the hair models to the input key strips. Although the base model matches the query strips at a high level, details deviate from the user’s intentions. The proposed blending and deformation algorithm produces results with realistic local details better following input guide strokes.