U-Net with ResNet Backbone for Garment Landmarking Purpose

TL;DR

This paper presents a heatmap-based landmark detection model using U-Net with ResNet backbone to identify key garment features on 2D images, facilitating 3D garment reconstruction and editing.

Contribution

It introduces a novel application of U-Net with ResNet backbone for garment landmark detection, enabling accurate 2D feature localization for 3D modeling.

Findings

The model effectively detects garment edges, corners, and interior regions.

It achieves moderate robustness with an appropriate loss function.

The approach supports 3D garment reconstruction and texture unwrapping.

Abstract

We build a heatmap-based landmark detection model to locate important landmarks on 2D RGB garment images. The main goal is to detect edges, corners and suitable interior region of the garments. This let us re-create 3D garments in modern 3D editing software by incorporate landmark detection model and texture unwrapping. We use a U-net architecture with ResNet backbone to build the model. With an appropriate loss function, we are able to train a moderately robust model.