We present a novel learning method using a two-stream network to predict cloth deformation for skeleton-based characters. The characters processed in our approach are not limited to humans, and can be other targets with skeleton-based representations such as fish or pets. We use a novel network architecture which consists of skeleton-based and mesh-based residual networks to learn the coarse features and wrinkle features forming the overall residual from the template cloth mesh. Our network may be used to predict the deformation for loose or tight-fitting clothing. The memory footprint of our network is low, thereby resulting in reduced computational requirements. In practice, a prediction for a single cloth mesh for a skeleton-based character takes about 7 ms on an nVidia GeForce RTX 3090 GPU. Compared to prior methods, our network can generate finer deformation results with details and wrinkles.

Abstract We propose a three‐stage network that utilizes a skinning‐based model to accurately predict dynamic cloth deformation. Our approach decomposes cloth deformation into three distinct components: static, coarse dynamic, and wrinkle dynamic components. To capture these components, we train our three‐stage network accordingly. In the first stage, the static component is predicted by constructing a static skinning model that incorporates learned joint increments and skinning weight increments. Then, in the second stage, the coarse dynamic component is added to the static skinning model by incorporating serialized skeleton information. Finally, in the third stage, the mesh sequence stage refines the prediction by incorporating the wrinkle dynamic component using serialized mesh information. We have implemented our network and used it in a Unity game scene, enabling real‐time prediction of cloth dynamics. Our implementation achieves impressive prediction speeds of approximately 3.65ms using an NVIDIA GeForce RTX 3090 GPU and 9.66ms on an Intel i7‐7700 CPU. Compared to SOTA methods, our network excels in accurately capturing fine dynamic cloth deformations.

Abstract We present a novel mesh‐based learning approach (N‐Cloth) for plausible 3D cloth deformation prediction. Our approach is general and can handle cloth or obstacles represented by triangle meshes with arbitrary topologies. We use graph convolution to transform the cloth and object meshes into a latent space to reduce the non‐linearity in the mesh space. Our network can predict the target 3D cloth mesh deformation based on the initial state of the cloth mesh template and the target obstacle mesh. Our approach can handle complex cloth meshes with up to 100 K triangles and scenes with various objects corresponding to SMPL humans, non‐SMPL humans or rigid bodies. In practice, our approach can be used to generate plausible cloth simulation at 30 – 45 fps on an NVIDIA GeForce RTX 3090 GPU. We highlight its benefits over prior learning‐based methods and physically‐based cloth simulators.

We present a fast iterated orthogonal projection (IOP) framework for smoke simulations. By modifying the IOP framework with a different means for convergence, our framework significantly reduces the number of iterations required to converge to the desired precision. Our new iteration framework adds a divergence redistributor component to IOP that can improve the impeded convergence logic of IOP. We tested Jacobi, GS and SOR as divergence redistributors and used the Multigrid scheme to generate a highly efficient Poisson solver. It provides a rapid convergence rate and requires less computation time. In all of our experiments, our method only requires 2-3 iterations to satisfy the convergence condition of 1e-5 and 5-7 iterations for 1e-10. Compared with the commonly used Incomplete Cholesky Preconditioned Conjugate Gradient(ICPCG) solver, our Poisson solver accelerates the overall speed to approximately 7- to 30-fold faster for grids ranging from 128(3) to 256(3). Our solver can accelerate more on larger grids because of the property that the iteration count required to satisfy the convergence condition is independent of the problem size. We use various experimental scenes and settings to demonstrate the efficiency of our method. In addition, we present a feasible method for both IOP and our fast IOP to support free surfaces.