GenSim: Unsupervised Generic Garment Simulator

Lokender Tiwari, Brojeshwar Bhowmick, Sanjana Sinha; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023, pp. 4169-4178

In this paper, we propose a novel generic garment simulator to drape a template 3D garment of arbitrary type, size, and topology onto an arbitrary 3D body shape and pose. Existing learning-based methods for 3D garment simulation methods train a single model for each garment type, with a fixed topology. Most of them use supervised learning, which requires huge training data that is expensive to acquire. Our method circumvents the above-mentioned limitations by proposing GenSim, a generic unsupervised method for garment simulation, that can generalize to garments of different sizes, topologies, body shapes, and poses, using a single trained model. Our proposed GenSim consists of (1) a novel body-motion-aware as-rigid-as-possible (ARAP) garment deformation module that initially deforms the template garment considering the underlying body as an obstacle and (2) a Physics Enforcing Network (PEN) that adds the corrections to the ARAP deformed garment to make it physically plausible. PEN uses multiple types of garments of arbitrary topology for training using physics-aware unsupervised losses. Experimental results show that our method significantly outperforms the existing state-of-the-art methods on the challenging CLOTH3D dataset and the VTO dataset. Unlike the unsupervised method PBNS, GenSim generalizes well on unseen garments with varying shapes, sizes, types, and topologies draped on different body shapes and poses.