Litcius/Paper detail

Real-Time Hair Simulation With Neural Interpolation

Qing Lyu, Menglei Chai, Xiang Chen, Kun Zhou

2020IEEE Transactions on Visualization and Computer Graphics11 citationsDOI

Abstract

Traditionally, reduced hair simulation methods are either restricted to heuristic approximations or bound to specific hairstyles. We introduce the first CNN-integrated framework for simulating various hairstyles. The approach produces visually realistic hairs with an interactive speed. To address the technical challenges, our hair simulation pipeline is designed as a two-stage process. First, we present a fully-convolutional neural interpolator as the backbone generator to compute dynamic weights for guide hair interpolation. Then, we adopt a second generator to produce fine-scale displacements to enhance the hair details. We train the neural interpolator with a dedicated loss function and the displacement generator with an adversarial discriminator. Experimental results demonstrate that our method is effective, efficient, and superior to the state-of-the-art on a wide variety of hairstyles. We further propose a performance-driven digital avatar system and an interactive hairstyle editing tool to illustrate the practical applications.

Topics & Concepts

Computer scienceInterpolation (computer graphics)Pipeline (software)Generator (circuit theory)HeuristicArtificial intelligenceVisualizationDisplacement (psychology)Computer visionAbstractionArtificial neural networkComputer graphics (images)Function (biology)Solid modelingAlgorithmComputer graphics3D Shape Modeling and AnalysisGenerative Adversarial Networks and Image SynthesisFace recognition and analysis
Real-Time Hair Simulation With Neural Interpolation | Litcius