Fast Complementary Dynamics
We propose a reduced-space elasto-dynamic solver that is well suited for augmenting rigged character animations with secondary motion. At the core of our method is a novel deformation subspace based on Linear Blend Skinning that overcomes many of the shortcomings prior subspace methods face. Our skinning subspace is parameterized entirely by a set of scalar weights, which we can obtain through a small, material-aware and rig-sensitive generalized eigenvalue problem. The resulting subspace can easily capture rotational motion and guarantees that the resulting simulation is rotation equivariant. We further propose a simple local-global solver for linear co-rotational elasticity and propose a clustering method to aggregate per-tetrahedra non-linear energetic quantities. The result is a compact simulation that is fully decoupled from the complexity of the mesh. We add secondary motion to rig animations in real-time by using a subspace for the physics simulation. We propose a linear blend s
Fast Complementary Dynamics via Skinning Eigenmodes Otman Benchekroun1, Jiayi Eris Zhang2, Siddhartha Chaudhuri3, Eitan Grinspun1, Yi Zhou3, Alec Jacobson 1, 3 1University of Toronto , 2Stanford University, 3Adobe Research SIGGRAPH North America 2023 Abstract We propose a reduced-space elasto-dynamic solver that is well suited for augmenting rigged character animations with secondary motion. At the core of our method is a novel deformation subspace based on Linear Blend Skinning that overcomes many of the shortcomings prior subspace methods face. Our skinning subspace is parameterized…
saved by
related reading
- Simplicits: Mesh-Free, Geometry-Agnostic, Elastic Simulationresearch.nvidia.com
- S4Darxiv.org
- Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboidsarxiv.org
- Fast Simulation of Mass-Spring Systemsusers.cs.utah.edu
- Optimizing Cubature for Efficient Integration of Subspace Deformationscs.cornell.edu
- A Unified Model for Motion-Conditioned Robot Co-designtransformer-transformer.github.io
- DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation | PDFarxiv.org
- mls.pdfcs.harvard.edu
- Generative Image Dynamicsgenerative-dynamics.github.io
- GitHub - yangtiming/Fast-SAM-3D-Body: [ECCV 2026] Fast SAM 3D Body: Accelerating SAM 3D Body for Real-Time Full-Body Human Mesh Recoverygithub.com
- Physics-Informed Diffusion Modelsarxiv.org
- Gray Crawfordgraycrawford.com