Differentiable Cloth Simulation for Inverse Problems
Explore this paper's citation graph
Summary
A differentiable cloth simulator that can be embedded as a layer in deep neural networks and provide an effective, robust framework for modeling cloth dynamics, self-collisions, and contacts is proposed.
- Type
- article
- Published
- 2019-09-06
- Cited by
- 217
- References
- 31
- OpenAlex
- https://openalex.org/W2970529185
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:202780283
Keywords
Differentiable function, Backpropagation, Curse of dimensionality, Computer science, Computation
References
- Rigid Body Simulation with Contact and Constraints
- Fast continuous collision detection using deforming non-penetration filters
- Data-driven elastic models for cloth: modeling and measurement
- Adaptive anisotropic remeshing for cloth simulation
- Bringing clothing into desired configurations with limited perception
- A fast finite element solution for cloth modelling
- Robust treatment of simultaneous collisions
- Estimating the Material Properties of Fabric from Video
- Large steps in cloth simulation
- Accelerating Eulerian Fluid Simulation With Convolutional Networks
- A DIFFERENTIABLE PHYSICS ENGINE FOR DEEP LEARNING IN ROBOTICS
- Deep learning in fluid dynamics
- OptNet: Differentiable Optimization as a Layer in Neural Networks
- ClothCap
- Learning-Based Cloth Material Recovery from Video
- RLlib: Abstractions for Distributed Reinforcement Learning
- Differentiable Physics and Stable Modes for Tool-Use and Manipulation Planning
- End-to-End Differentiable Physics for Learning and Control
- ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics
- GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping
Cited by
- Differentiable Molecular Simulations for Control and Learning
- Cloth in the Wind: A Case Study of Physical Measurement Through Simulation
- Learning to Measure the Static Friction Coefficient in Cloth Contact
- Visual Grounding of Learned Physical Models
- Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers
- ADD
- Differentiable Physics Simulation
- Augmenting Differentiable Simulators with Neural Networks to Close the Sim2Real Gap
- Deep Detail Enhancement for Any Garment
- Fully Convolutional Graph Neural Networks for Parametric Virtual Try‐On
- Reality-Assisted Evolution of Soft Robots through Large-Scale Physical Experimentation: A Review
- Machine learning for digital try-on: Challenges and progress
- NeuralSim: Augmenting Differentiable Simulators with Neural Networks
- An End-to-End Differentiable but Explainable Physics Engine for Tensegrity Robots: Modeling and Control
- Spring-Rod System Identification via Differentiable Physics Engine
- Learning Physical Constraints with Neural Projections
- Functional optimization of fluidic devices with differentiable stokes flow
- A First Principles Approach for Data-Efficient System Identification of Spring-Rod Systems via Differentiable Physics Engines
- Codimensional incremental potential contact
- SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements
Related papers
- End-to-End Differentiable Physics for Learning and Control
- Flexible neural representation for physics prediction
- Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids
- A DIFFERENTIABLE PHYSICS ENGINE FOR DEEP LEARNING IN ROBOTICS
- Interaction Networks for Learning about Objects, Relations and Physics
- Interactive Differentiable Simulation
- Scalable Differentiable Physics for Learning and Control
- PyTorch: An Imperative Style, High-Performance Deep Learning Library