DIG: Draping Implicit Garment over the Human Body
This addresses the need for flexible and differentiable garment draping in computer graphics and vision, with incremental improvements over existing data-driven methods.
The paper tackles the problem of draping garments of arbitrary topology over human bodies in a differentiable way, achieving more accurate garment reconstruction and deformation compared to state-of-the-art methods and enabling joint recovery of body and garment parameters from images.
Existing data-driven methods for draping garments over human bodies, despite being effective, cannot handle garments of arbitrary topology and are typically not end-to-end differentiable. To address these limitations, we propose an end-to-end differentiable pipeline that represents garments using implicit surfaces and learns a skinning field conditioned on shape and pose parameters of an articulated body model. To limit body-garment interpenetrations and artifacts, we propose an interpenetration-aware pre-processing strategy of training data and a novel training loss that penalizes self-intersections while draping garments. We demonstrate that our method yields more accurate results for garment reconstruction and deformation with respect to state of the art methods. Furthermore, we show that our method, thanks to its end-to-end differentiability, allows to recover body and garments parameters jointly from image observations, something that previous work could not do.