3D Clothing modeling and datasets play crucial role in the entertainment,
animation, and digital fashion industries. Existing work often lacks detailed
semantic understanding or uses synthetic datasets, lacking realism and
personalization. To address this, we first introduce CloSe-D: a novel
large-scale dataset containing 3D clothing segmentation of 3167 scans, covering
a range of 18 distinct clothing classes. Additionally, we propose CloSe-Net,
the first learning-based 3D clothing segmentation model for fine-grained
segmentation from colored point clouds. CloSe-Net uses local point features,
body-clothing correlation, and a garment-class and point features-based
attention module, improving performance over baselines and prior work. The
proposed attention module enables our model to learn appearance and
geometry-dependent clothing prior from data. We further validate the efficacy
of our approach by successfully segmenting publicly available datasets of
people in clothing. We also introduce CloSe-T, a 3D interactive tool for
refining segmentation labels. Combining the tool with CloSe-T in a continual
learning setup demonstrates improved generalization on real-world data.
Dataset, model, and tool can be found at
this https URL

该研究介绍了 CloSe-D 数据集，其中包含 3167 个扫描的 3D 服装分割，覆盖了 18 个不同的服装类别；同时提出了 CloSe-Net，第一个基于学习的用于彩色点云的精细分割的 3D 服装分割模型，该模型利用局部点特征、身体服装相关性和基于服装类别和点特征的注意力模块，提高了性能。CloSe-T 是一个用于细化分割标签的 3D 交互工具，在实际数据上展示了改进的泛化能力。

CloSe: 一个 3D 服装分割数据集和模型

CloSe: A 3D Clothing Segmentation Dataset and Model

Clothing segmentation and fine-grained attribute recognition are challenging
tasks at the crossing of computer vision and fashion, which segment the entire
ensemble clothing instances as well as recognize detailed attributes of the
clothing products from any input human images. Many new models have been
developed for the tasks in recent years, nevertheless the segmentation accuracy
is less than satisfactory in case of layered clothing or fashion products in
different scales. In this paper, a new DEtection TRansformer (DETR) based
method is proposed to segment and recognize fine-grained attributes of ensemble
clothing instances with high accuracy. In this model, we propose a
\textbf{multi-layered attention module} by aggregating features of different
scales, determining the various scale components of a single instance, and
merging them together. We train our model on the Fashionpedia dataset and
demonstrate our method surpasses SOTA models in tasks of layered clothing
segmentation and fine-grained attribute recognition.

本文提出了一种新型 DETR 方法，在 Fashionpedia 数据集上训练，通过采用多层注意力模块来聚合不同规模的特征，识别出整体服装实例的细粒度属性并实现服装的分割，超越了领域内之前最先进的模型。