U-Net with ResNet Backbone for Garment Landmarking Purpose
This work addresses garment landmarking for 3D editing applications, but it appears incremental as it applies existing methods to a new domain.
The researchers tackled the problem of detecting landmarks on 2D RGB garment images to enable 3D garment recreation, achieving a moderately robust model using a U-Net with ResNet backbone and appropriate loss function.
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.