← ArchivePaper2017
ClothCap: Seamless 4D Clothing Capture and Retargeting
4D scanning system that captures detailed clothing geometry and body motion simultaneously, enabling garment retargeting to new body shapes.
Abstract
Designing and simulating realistic clothing is challenging. Previous methods addressing the capture of clothing from 3D scans have been limited to single garments and simple motions, lack detail, or require specialized texture patterns. Here we address the problem of capturing regular clothing on fully dressed people in motion. People typically wear multiple pieces of clothing at a time. To estimate the shape of such clothing, track it over time, and render it believably, each garment must be segmented from the others and the body. Our ClothCap approach uses a new multi-part 3D model of clothed bodies, automatically segments each piece of clothing, estimates the minimally clothed body shape and pose under the clothing, and tracks the 3D deformations of the clothing over time. We estimate the garments and their motion from 4D scans; that is, high-resolution 3D scans of the subject in motion at 60 fps. ClothCap is able to capture a clothed person in motion, extract their clothing, and retarget the clothing to new body shapes; this provides a step towards virtual try-on.
How to read this
- Category
- Capture system: 4D clothing capture and retargeting
- Contributions
- A multi-part 3D model of clothed bodies that automatically segments each garment from the others and the body
- Estimation of the minimally clothed body shape and pose under the clothing and tracking of garment 3D deformations over time from 4D scans (60 fps)
- Retargeting of captured clothing to new body shapes as a step toward virtual try-on
- Context
- Builds on Loper et al.'s SMPL skinned body model, extending it to a multi-part clothed-body representation for capturing regular clothing on people in motion.Builds on: SMPL: A Skinned Multi-Person Linear Model
- Correctness
- Demonstrated on high-resolution 4D scans of fully dressed subjects in motion; it assumes garments can be segmented and an underlying body inferred, so results depend on scan quality and the model's part decomposition rather than on physical simulation.
- Clarity
- Accessible in motivation; a first pass conveys the capture-segment-retarget pipeline, a second pass clarifies the multi-part model and tracking formulation.
- How to read it
- Focus on the multi-part model and how the under-clothing body is estimated; a second pass pays off for the segmentation and tracking math if you work in capture or try-on.
Builds on
Built upon by
Nothing yet.
Related work
- SMPL: A Skinned Multi-Person Linear Model 2015 / SIGGRAPH Asia
- Learning-Based Animation of Clothing for Virtual Try-On 2019 / CGF
- SMPLicit: Topology-aware Generative Model for Clothed People 2021 / CVPR
- SNUG: Self-Supervised Neural Dynamic Garments 2022 / CVPR
Keywords
This page summarises the entry and links to its original source. The archive never hosts or redistributes the publication itself.Show it in the full archive list →