Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance Flow

About

Virtual try-on is a critical image synthesis task that aims to transfer clothes from one image to another while preserving the details of both humans and clothes. While many existing methods rely on Generative Adversarial Networks (GANs) to achieve this, flaws can still occur, particularly at high resolutions. Recently, the diffusion model has emerged as a promising alternative for generating high-quality images in various applications. However, simply using clothes as a condition for guiding the diffusion model to inpaint is insufficient to maintain the details of the clothes. To overcome this challenge, we propose an exemplar-based inpainting approach that leverages a warping module to guide the diffusion model's generation effectively. The warping module performs initial processing on the clothes, which helps to preserve the local details of the clothes. We then combine the warped clothes with clothes-agnostic person image and add noise as the input of diffusion model. Additionally, the warped clothes is used as local conditions for each denoising process to ensure that the resulting output retains as much detail as possible. Our approach, namely Diffusion-based Conditional Inpainting for Virtual Try-ON (DCI-VTON), effectively utilizes the power of the diffusion model, and the incorporation of the warping module helps to produce high-quality and realistic virtual try-on results. Experimental results on VITON-HD demonstrate the effectiveness and superiority of our method.

Junhong Gou, Siyu Sun, Jianfu Zhang, Jianlou Si, Chen Qian, Liqing Zhang• 2023

Related benchmarks

TaskDatasetResultRank
Virtual Try-OnVITON-HD (test)
SSIM89
48
Virtual Try-OnVITON-HD 1.0 (test)
FID8.754
27
Virtual Try-OnVITON paired HD (test)
FID5.52
19
Virtual Try-OnVITON-HD unpaired 1.0 (test)
FID8.75
14
Virtual Try-OnVITON-HD high-resolution (test)
SSIM0.88
13
Virtual Try-OnStreetVTON (test)
FIDu20.95
11
Virtual Try-OnWildVTON (test)
FIDu35.66
11
Image-based Virtual Try-OnVITON-HD paired unpaired
SSIM0.89
11
Virtual Try-OnDressCode upper-body (test)
SSIM0.903
9
Virtual Try-OnSHHQ 1.0 (test)
FID24.368
8
Showing 10 of 13 rows

Other info

Follow for update