IGR: Improving Diffusion Model for Garment Restoration from Person Image
This work addresses garment restoration for virtual try-on applications, representing an incremental improvement over existing methods.
The paper tackles the problem of garment restoration from person images by proposing an improved diffusion model that uses two garment extractors and garment fusion blocks to integrate features into the denoising process, resulting in effective preservation of garment identity and high-quality restorations in challenging scenarios.
Garment restoration, the inverse of virtual try-on task, focuses on restoring standard garment from a person image, requiring accurate capture of garment details. However, existing methods often fail to preserve the identity of the garment or rely on complex processes. To address these limitations, we propose an improved diffusion model for restoring authentic garments. Our approach employs two garment extractors to independently capture low-level features and high-level semantics from the person image. Leveraging a pretrained latent diffusion model, these features are integrated into the denoising process through garment fusion blocks, which combine self-attention and cross-attention layers to align the restored garment with the person image. Furthermore, a coarse-to-fine training strategy is introduced to enhance the fidelity and authenticity of the generated garments. Experimental results demonstrate that our model effectively preserves garment identity and generates high-quality restorations, even in challenging scenarios such as complex garments or those with occlusions.