Related papers: Cloth Animation with Time-dependent Persistent Wri…
3D reconstruction of highly deformable surfaces (e.g. cloths) from monocular RGB videos is a challenging problem, and no solution provides a consistent and accurate recovery of fine-grained surface details. To account for the ill-posed…
Computations have helped elucidate the dynamics of Earth's mantle for several decades already. The numerical methods that underlie these simulations have greatly evolved within this time span, and today include dynamically changing and…
Over times shorter than that required for relaxation of enthalpy, a liquid can exhibit striking heterogeneities. The picture of these heterogeneities is complex with transient patches of rigidity, irregular yet persistent, intersected by…
We present an approach to continuous perception for robotic laundry tasks. Our assumption is that the visual prediction of a garment's shapes and weights is possible via a neural network that learns the dynamic changes of garments from…
Many interesting shapes appearing in the biological world are formed by the onset of mechanical instability. In this work we consider how the build-up of residual stress can cause a solid to buckle. In all past studies a fictitious…
We study the indentation of a thin elastic film floating at the surface of a liquid. We focus on the onset of radial wrinkles at a threshold indentation depth and the evolution of the wrinkle pattern as indentation progresses far beyond…
Self-occlusion is challenging for cloth manipulation, as it makes it difficult to estimate the full state of the cloth. Ideally, a robot trying to unfold a crumpled or folded cloth should be able to reason about the cloth's occluded…
We present a novel learning method to predict the cloth deformation for skeleton-based characters with a two-stream network. The characters processed in our approach are not limited to humans, and can be other skeletal-based representations…
Cloth manipulation is challenging due to its highly complex dynamics, near-infinite degrees of freedom, and frequent self-occlusions, which complicate both state estimation and dynamics modeling. Inspired by recent advances in generative…
Dynamics simulation with frictional contacts is important for a wide range of applications, from cloth simulation to object manipulation. Recent methods using smoothed lagged friction forces have enabled robust and differentiable simulation…
Garment restoration, the inverse of virtual try-on task, focuses on restoring standard garment from a person image, requiring accurate capture of garment details. However, existing methods often fail to preserve the identity of the garment…
A variety of complex fluids consist in soft, round objects (foams, emulsions, assemblies of copolymer micelles or of multilamellar vesicles -- also known as onions). Their dense packing induces a slight deviation from their prefered…
It is extremely challenging to create an animatable clothed human avatar from RGB videos, especially for loose clothes due to the difficulties in motion modeling. To address this problem, we introduce a novel representation on the basis of…
A controlled surface wrinkling pattern has been widely used in diverse applications, such as stretchable electronics, smart windows, and haptics. Here, we focus on hexagonal wrinkling patterns because of their great potentials in realizing…
We present a self-supervised method to learn dynamic 3D deformations of garments worn by parametric human bodies. State-of-the-art data-driven approaches to model 3D garment deformations are trained using supervised strategies that require…
Soft tissue simulation in virtual environments is becoming increasingly important for medical applications. However, the high deformability of soft tissue poses significant challenges. Existing methods rely on segmentation, meshing and…
We study the problem of learning physical object representations for robot manipulation. Understanding object physics is critical for successful object manipulation, but also challenging because physical object properties can rarely be…
Parametric 3D body models like SMPL only represent minimally-clothed people and are hard to extend to clothing because they have a fixed mesh topology and resolution. To address these limitations, recent work uses implicit surfaces or point…
Designing real and virtual garments is becoming extremely demanding with rapidly changing fashion trends and increasing need for synthesizing realistic dressed digital humans for various applications. This necessitates creating simple and…
Kinesthetic garments provide physical feedback on body posture and motion through tailored distributions of reinforced material. Their ability to selectively stiffen a garment's response to specific motions makes them appealing for…