A Layered Model of Human Body and Garment Deformation

Abstract

In this paper we present a framework for learning a three layered model of human shape, pose and garment deformation. The proposed deformation model provides intuitive control over the three parameters independently, while producing aesthetically pleasing deformations of both the garment and the human body. The shape and pose deformation layers of the model are trained on a rich dataset of full body 3D scans of human subjects in a variety of poses. The garment deformation layer is trained on animated mesh sequences of dressed actors and relies on a novel technique for human shape and posture estimation under clothing.The key contribution of this paper is that we consider garment deformations as the residual transformations between a naked mesh and the dressed mesh of the same subject.

Computing Temporal Alignments of Human Motion Sequences in Wide Clothing Using Geodesic Patches

“…initialization for the computation of near-isometric partial matches. This step takes advantage of recent robust methods that use statistical human body models to estimate the naked human body shape under clothing [11,23,14,17,24]. In our implementation, we use an automatic method that estimates the naked body shape in motion under clothing based on a 3D input sequence [24].…”

“…Instead, we estimate the body shape under the cloth and then automatically transfer the anatomical landmarks from the body shape to the cloth. Many methods for human body shape estimation under clothing have been proposed [11,23,14,17]. We use the recent method of Yang et al [24] since it works for moving shapes and is fully automatic.…”

Multi-Garment Net: Learning to Dress 3D People From Images

“…Very few approaches have shown models learned from real data. Given a dynamic scan sequence, Neophytou et al [42] learn a two layer model (body and clothing) and use it to dress novel shapes. A similar model has been recently proposed [61], where the clothing layer is associated to the body in a fuzzy fashion.…”

Analyzing Clothing Layer Deformation Statistics of 3D Human Motions

“…Thanks to laser scanners, depth cameras, and multi-camera system, it is now possible to capture and reconstruct 3D human motion sequences as raw mesh sequences [4,10,23], and recent processing algorithms (reviewed in the following) allow to extract semantic information from the raw data. A recent line of work leverages this rich source of data by using captured sequences to learn the deformation of the clothing layer [22,25]. Neophytou and Hilton [22] propose a method that trains from a single subject in fixed clothing and allows to change the body shape and motion after training.…”

“…A recent line of work leverages this rich source of data by using captured sequences to learn the deformation of the clothing layer [22,25]. Neophytou and Hilton [22] propose a method that trains from a single subject in fixed clothing and allows to change the body shape and motion after training. Pons-Moll et al [25] extract the body shape and individual pieces of clothing from a raw capture sequence and use this information to trans-fer the captured clothing to new body shapes.…”