Cloth Simulation News
The latest Cloth Simulation coverage curated for game developers.
A new cloth-simulation pipeline targets one of the hardest garment problems: persistent wrinkles that survive motion and washing-like cycles. The work pairs a 101-fabric dataset with a differentiable simulator so …
A new cloth solver claims the first r-adaptive approach for modern pipelines with frictional contact, aiming at sharper wrinkles and folds without fixed-mesh overhead. It tackles two common failure modes …
A new graph-based ML pipeline reconstructs garment stitching from 2D sewing patterns, including coarse panel connectivity and fine seam correspondences. That could cut down the expert hand-authoring still needed to …
Cloth simulation is getting a Transformer treatment that aims to scale beyond one-off setups. ClothTransformer models garments, robotic manipulation, and free-fall collisions in a shared latent space, with reported error …
A 5D point-cloud garment representation tries to bridge the gap between fast, high-level generation and the messy reality of editing both sewing patterns and draped 3D cloth. For teams working …
HyperBones targets a long-standing cloth-sim problem: getting loose garments to move plausibly at real-time rates. The system uses virtual bones, a lightweight neural correction layer, and UV-space wrinkle recovery to …
A pose-conditioned 3D Gaussian avatar can now carry a learned latent state that evolves over time, which helps with loose clothing and other motion that pose alone can't explain. The …
A new method for estimating cloth elasticity parameters could revolutionize how graphics programmers create realistic clothing simulations. By focusing on wrinkling as a key factor, this approach simplifies the process …
A new differentiable simulation framework targets one of the hardest problems in graphics and robotics: stable gradients through frictional contact. Built as a fully GPU-accelerated solver, it aims to keep …
A new B-spline finite element method enhances cloth simulation, achieving a 2x speedup over traditional linear methods. This advancement is particularly relevant for graphics programmers seeking improved accuracy and visual …
SpringTime introduces a new framework for simulating cloth materials that significantly reduces computational demands. By utilizing motion observations, it learns material properties without the stiffness issues common in traditional methods. …
FNOpt introduces a groundbreaking self-supervised cloth simulation framework that optimizes time integration using Fourier neural operators. This innovation allows developers to achieve stable and accurate cloth dynamics across various resolutions …