DeepWrinkles: Accurate and Realistic Clothing Modeling

Abstract

We present a novel method to generate accurate and realistic clothing deformation from real data capture. Previous methods for realistic cloth modeling mainly rely on intensive computation of physics-based simulation (with numerous heuristic parameters), while models reconstructed from visual observations typically suffer from lack of geometric details. Here, we propose an original framework consisting of two modules that work jointly to represent global shape deformation as well as surface details with high fidelity. Global shape deformations are recovered from a subspace model learned from 3D data of clothed people in motion, while high frequency details are added to normal maps created using a conditional Generative Adversarial Network whose architecture is designed to enforce realism and temporal consistency. This leads to unprecedented high-quality rendering of clothing deformation sequences, where fine wrinkles from (real) high resolution observations can be recovered. In addition, as the model is learned independently from body shape and pose, the framework is suitable for applications that require retargeting (e.g., body animation). Our experiments show original high quality results with a flexible model. We claim an entirely data-driven approach to realistic cloth wrinkle generation is possible.

arXiv comment18 pages, 12 figures, 15th European Conference on Computer Vision (ECCV) 2018, Oral Presentation

References in corpus (1)

• Sequence to Sequence Learning with Neural Networks

Cited by in corpus (16)

• Fashion Meets Computer Vision: A Survey
• Neural Human Video Rendering by Learning Dynamic Textures and Rendering-to-Video Translation
• Multi-feature super-resolution network for cloth wrinkle synthesis
• Towards Multi-pose Guided Virtual Try-on Network
• DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Compare
• Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images
• ARCH: Animatable Reconstruction of Clothed Humans
• ARCH++: Animation-Ready Clothed Human Reconstruction Revisited
• SimulCap : Single-View Human Performance Capture with Cloth Simulation
• BCNet: Learning Body and Cloth Shape from A Single Image
• Neural 3D Clothes Retargeting from a Single Image
• Self-Supervised Collision Handling via Generative 3D Garment Models for Virtual Try-On
• 3D Appearance Super-Resolution with Deep Learning
• Recovering Geometric Information with Learned Texture Perturbations
• Alternating ConvLSTM: Learning Force Propagation with Alternate State Updates
• WAS-VTON: Warping Architecture Search for Virtual Try-on Network