paper-with-me

Papers

Improving Diffusion Models for Authentic Virtual Try-on in the Wild

2024-03-08 · Yisol Choi, Sangkyung Kwak, Kyungmin Lee, Hyungwon Choi, Jinwoo Shin

This paper considers image-based virtual try-on, which renders an image of a person wearing a curated garment, given a pair of images depicting the person and the garment, respectively. Previous works adapt existing exemplar-based inpainting diffusion models for virtual try-on to improve the naturalness of the generated visuals compared to other methods (e.g., GAN-based), but they fail to preserve the identity of the garments. To overcome this limitation, we propose a novel diffusion model that improves garment fidelity and generates authentic virtual try-on images. Our method, coined IDM-VTON, uses two different modules to encode the semantics of garment image; given the base UNet of the diffusion model, 1) the high-level semantics extracted from a visual encoder are fused to the cross-attention layer, and then 2) the low-level features extracted from parallel UNet are fused to the self-attention layer. In addition, we provide detailed textual prompts for both garment and person images to enhance the authenticity of the generated visuals. Finally, we present a customization method using a pair of person-garment images, which significantly improves fidelity and authenticity. Our experimental results show that our method outperforms previous approaches (both diffusion-based and GAN-based) in preserving garment details and generating authentic virtual try-on images, both qualitatively and quantitatively. Furthermore, the proposed customization method demonstrates its effectiveness in a real-world scenario. More visualizations are available in our project page: https://idm-vton.github.io

📄 PDF Abstract BibTeX arXiv:2403.05139

Code (1)

yisol/IDM-VTON 공식 구현 pytorch

Tasks

Virtual Try-on

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
Inpainting Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.
BASE 설명 없음

Similar Papers 제목 키워드 기반

FitVTON: Fit-aware Virtual Try-On via Body-Garment Size Control

2026-06-10 · Yiqun Ning, Ao Shen, Chenhang He, Lei Zhang arxiv

While diffusion-based virtual try-on has achieved impressive visual realism, most methods treat the task as 2D inpainting, prioritizing texture preservation over physical plausibility. Consequently, they often produce pl…

Virtual Try-on

A Two-stage Personalized Virtual Try-on Framework with Shape Control and Texture Guidance

2023-12-24 · Shufang Zhang, Minxue Ni, Lei Wang, Wenxin Ding 외

The Diffusion model has a strong ability to generate wild images. However, the model can just generate inaccurate images with the guidance of text, which makes it very challenging to directly apply the text-guided genera…

Virtual Try-on

BooW-VTON: Boosting In-the-Wild Virtual Try-On via Mask-Free Pseudo Data Training

2024-08-12 · CVPR 2025 1 · Xuanpu Zhang, Dan Song, Pengxin Zhan, Tianyu Chang 외

Image-based virtual try-on is an increasingly popular and important task to generate realistic try-on images of the specific person. Recent methods model virtual try-on as image mask-inpaint task, which requires masking …

Data AugmentationVirtual Try-on

Perceptual Quality Assessment of Virtual Reality Videos in the Wild

2022-06-13 · Wen Wen, Mu Li, Yiru Yao, Xiangjie Sui 외

Investigating how people perceive virtual reality (VR) videos in the wild (i.e., those captured by everyday users) is a crucial and challenging task in VR-related applications due to complex authentic distortions localiz…

Saliency DetectionVideo Quality Assessment

Street TryOn: Learning In-the-Wild Virtual Try-On from Unpaired Person Images

2023-11-27 · Aiyu Cui, Jay Mahajan, Viraj Shah, Preeti Gomathinayagam 외

Most virtual try-on research is motivated to serve the fashion business by generating images to demonstrate garments on studio models at a lower cost. However, virtual try-on should be a broader application that also all…

Image GenerationSemantic SegmentationVirtual Try-onVirtual Try-on (Model2Street)+2