Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.08573 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915088921788416 |
|---|---|
| author | Xarchakos, Ioannis Koukopoulos, Theodoros |
| author_facet | Xarchakos, Ioannis Koukopoulos, Theodoros |
| contents | The fashion industry is increasingly leveraging computer vision and deep learning technologies to enhance online shopping experiences and operational efficiencies. In this paper, we address the challenge of generating high-fidelity tiled garment images essential for personalized recommendations, outfit composition, and virtual try-on systems from photos of garments worn by models. Inspired by the success of Latent Diffusion Models (LDMs) in image-to-image translation, we propose a novel approach utilizing a fine-tuned StableDiffusion model. Our method features a streamlined single-stage network design, which integrates garmentspecific masks to isolate and process target clothing items effectively. By simplifying the network architecture through selective training of transformer blocks and removing unnecessary crossattention layers, we significantly reduce computational complexity while achieving state-of-the-art performance on benchmark datasets like VITON-HD. Experimental results demonstrate the effectiveness of our approach in producing high-quality tiled garment images for both full-body and half-body inputs. Code and model are available at: https://github.com/ixarchakos/try-off-anyone |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_08573 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TryOffAnyone: Tiled Cloth Generation from a Dressed Person Xarchakos, Ioannis Koukopoulos, Theodoros Computer Vision and Pattern Recognition The fashion industry is increasingly leveraging computer vision and deep learning technologies to enhance online shopping experiences and operational efficiencies. In this paper, we address the challenge of generating high-fidelity tiled garment images essential for personalized recommendations, outfit composition, and virtual try-on systems from photos of garments worn by models. Inspired by the success of Latent Diffusion Models (LDMs) in image-to-image translation, we propose a novel approach utilizing a fine-tuned StableDiffusion model. Our method features a streamlined single-stage network design, which integrates garmentspecific masks to isolate and process target clothing items effectively. By simplifying the network architecture through selective training of transformer blocks and removing unnecessary crossattention layers, we significantly reduce computational complexity while achieving state-of-the-art performance on benchmark datasets like VITON-HD. Experimental results demonstrate the effectiveness of our approach in producing high-quality tiled garment images for both full-body and half-body inputs. Code and model are available at: https://github.com/ixarchakos/try-off-anyone |
| title | TryOffAnyone: Tiled Cloth Generation from a Dressed Person |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.08573 |