New fabric dataset and simulator improve persistent wrinkle modeling
Learnable Persistent Wrinkle Formation in Cloth Simulation
Graphics
Summary
Many clothes keep wrinkles even after being stretched or bent because of their unique material properties. The authors created a new dataset of over 100 fabrics that captures how these materials behave under repeated stretching and releasing. They also developed a special simulation tool that learns fabric-specific wrinkle patterns by using this data. Their approach helps create more realistic and lasting wrinkles in digital clothing animations, making virtual fabrics look and move more like real ones.
What this means in practice
- •For digital garment designers: Simulate realistic persistent wrinkles on virtual clothes tailored to specific fabric types for improved visual authenticity.
- •For animation studios: Create more believable cloth animations by using learned fabric parameters to reproduce natural wrinkle behavior over time.
Authors
Deshan Gong, Ningtao Mao, Xiaoyuan Yang, Xinyu Lu, He Wang, Taku Komura
Abstract
The mechanical memory of fabrics often leads to persistent wrinkles, which reflect key physical properties and habitual wear patterns. Simulating these wrinkles accurately is essential for visual plausibility in digital garments, yet no dedicated approach exists for inferring the parameters that govern their formation due to the lack of precise datasets and estimation methods. We introduce Fabric-101, an inclusive, accurate, and extendable fabric dataset comprising over 101 common fabrics following textile standards. Unlike existing datasets, it captures three physically distinct deformation components (i.e., self-recoverable (elastic), recoverable (friction-driven), and unrecoverable (plastic)), from cyclic loading-unloading measurements. Building on this data, we propose a differentiable cloth simulator combining an elasto-plastic model with friction, designed to capture recoverable and unrecoverable wrinkle formation. Our simulator is differentiable and uses adjoint method to learn fabric physical parameters from the measured hysteresis curves, learning fabric-specific wrinkle behaviors. Through extensive experiments, we demonstrate that our model reproduces persistent wrinkles that are visually and physically similar to real fabrics across diverse materials and motions. Dataset and code are available in https://github.com/GongDeshan/Fabric_101_for_Wrinkles.