Dr.Hair: Reconstructing Scalp-Connected Hair Strands without Pre-training via Differentiable Rendering of Line Segments
This addresses the labor-intensive and costly domain gap issues in hair reconstruction for the film and gaming industries, offering a more efficient alternative to pre-training methods.
The paper tackles the problem of reconstructing scalp-connected hair strands from surface images without pre-training, proposing an optimization-based method that uses differentiable rendering of line segments and achieves robust and accurate inverse rendering with significant speed improvements.
In the film and gaming industries, achieving a realistic hair appearance typically involves the use of strands originating from the scalp. However, reconstructing these strands from observed surface images of hair presents significant challenges. The difficulty in acquiring Ground Truth (GT) data has led state-of-the-art learning-based methods to rely on pre-training with manually prepared synthetic CG data. This process is not only labor-intensive and costly but also introduces complications due to the domain gap when compared to real-world data. In this study, we propose an optimization-based approach that eliminates the need for pre-training. Our method represents hair strands as line segments growing from the scalp and optimizes them using a novel differentiable rendering algorithm. To robustly optimize a substantial number of slender explicit geometries, we introduce 3D orientation estimation utilizing global optimization, strand initialization based on Laplace's equation, and reparameterization that leverages geometric connectivity and spatial proximity. Unlike existing optimization-based methods, our method is capable of reconstructing internal hair flow in an absolute direction. Our method exhibits robust and accurate inverse rendering, surpassing the quality of existing methods and significantly improving processing speed.