DeepIron: Predicting Unwarped Garment Texture from a Single Image
This addresses realistic 3D clothing reconstruction for applications like avatar creation and virtual try-on, representing an incremental advancement in texture prediction.
The paper tackles the problem of reconstructing 3D garment textures from a single image with pose, aiming to generate unwarped texture images for sewing patterns, and demonstrates effectiveness through comparisons and ablation studies.
Realistic reconstruction of 3D clothing from an image has wide applications, such as avatar creation and virtual try-on. This paper presents a novel framework that reconstructs the texture map for 3D garments from a single image with pose. Assuming that 3D garments are modeled by stitching 2D garment sewing patterns, our specific goal is to generate a texture image for the sewing patterns. A key component of our framework, the Texture Unwarper, infers the original texture image from the input clothing image, which exhibits warping and occlusion of texture due to the user's body shape and pose. The Texture Unwarper effectively transforms between the input and output images by mapping the latent spaces of the two images. By inferring the unwarped original texture of the input garment, our method helps reconstruct 3D garment models that can show high-quality texture images realistically deformed for new poses. We validate the effectiveness of our approach through a comparison with other methods and ablation studies.