文章详情

摘要

文章调研了国内外在虚拟试衣领域的研究现状，包括基于对抗生成网络和扩散模型等技术的应用情况，并总结了虚拟试衣各数据集。在相关理论基础上，对基于外观流和扩散模型的虚拟试衣进行研究。首先运用基于外观流的局部流全局解析（Local-Flow Global-Parsing, LFGP）模型对目标服装进行变形，使其符合人体姿势；接着使用扩散模型对人物和服装进行合成，并对细节进行处理，完成最终试衣。定性和定量分析实验结果表明，相较于以往研究，基于LFGP的服装变形可以更好地处理服装细节以及人物与服装的连接部分，扩散模型在试衣合成处理时也可以在保持真实性的同时提高灵活度，为虚拟试衣技术的进一步研究提供参考。

关键词

虚拟试衣；深度学习；扩散模型；外观流

参考文献

1. [1] EHARA J，SAITO H. Texture Overlay for Virtual Clothing Based on PCA of Silhouettes [C]//2006 IEEE/ACM International Symposium on Mixed and Augmented Reality.Santa Barbara：IEEE，2006：139-142.
2. [2] TANAKA H，SAITO H. Texture Overlay onto Flexible Object with PCA of Silhouettes and K-means Method for Search into Database [C]//MVA 2009 IAPR Conference on Machine Vision Applications.Yokohama：MVA，2009：5-8.
3. [3] HAN X T，WU Z X，WU Z，et al. VITON: An Image-based Virtual Try-on Network [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City：IEEE，2018：7543-7552.
4. [4] WANG B C，ZHENG H B，LIANG X D，et al. Toward Characteristic-Preserving Image-Based Virtual Try-on Network [C]//Computer Vision-ECCV 2018.Munich：Springer Nature，2018：607-623.
5. [5] HAN X T，HUANG W L，HU X J，et al. ClothFlow: A Flow-based Model for Clothed Person Generation [C]//2019 IEEE/CVF International Conference on Computer Vision.Seoul：IEEE，2019：10470-10479.
6. [6] CHOI S，PARK S，LEE M，et al. VITON-HD: High-resolution Virtual Try-on via Misalignment-aware Normalization [C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Nashville：IEEE，2021：14126-14135.
7. [7] LEE S，GU G，PARK S，et al. High-resolution Virtual Try-on with Misalignment and Occlusion-Handled Conditions [C]//Computer Vision-ECCV 2022.Tel Aviv：Springer Nature，2022：204-219.
8. [8] XIE Z Y，HUANG Z Y，DONG X，et al. GP-VTON: Towards General Purpose Virtual Try-on via Collaborative Local-flow Global-parsing Learning [C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Vancouver：IEEE，2023：23550-23559.
9. [9] HO J，JAIN A，ABBEEL P. Denoising Diffusion Probabilistic Models [J/OL].arXiv:2006.11239 [cs.LG].（2020-06-19）.https://arxiv.org/abs/2006.11239v2.
10. [10] BALDRATI A，MORELLI D，CARTELLA G，et al. Multimodal Garment Designer: Human-centric Latent Diffusion Models for Fashion Image Editing [C]//2023 IEEE/CVF International Conference on Computer Vision.Paris：IEEE，2023：23336-23345.
11. [11] GOU J H，SUN S Y，ZHANG J F，et al. Taming the Power of Diffusion Models for High-quality Virtual Try-on with Appearance Flow [C]//31st ACM International Conference on Multimedia.Ottawa：ACM，2023：7599-7607.
12. [12] MORELLI D，FINCATO M，CORNIA M，et al. Dress Code: High-resolution Multi-category Virtual Try-on [C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops.New Orleans：IEEE，2022：2230-2234.
13. [13] ZHOU T H，TULSIANI S，SUN W L，et al. View Synthesis by Appearance Flow [C]//Computer Vision-ECCV 2016.Amsterdam：Springer Nature，2016：286-301.
14. [14] WANG M H，WANG Q，CHANUSSOT J，et al. L0-L1 Hybrid Total Variation Regularization and its Applications on Hyperspectral Image Mixed Noise Removal and Compressed Sensing [J].IEEE Transactions on Geoscience and Remote Sensing，2021，59（9）：7695-7710.
15. [15] ROMBACH R，BLATTMANN A，LORENZ D，et al. High-resolution Image Synthesis with Latent Diffusion Models [C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition.New Orleans：IEEE，2022：10674-10685.
16. [16] CHENG B W，MISRA I，SCHWING A G，et al. Masked-Attention Mask Transformer for Universal Image Segmentation [C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition.New Orleans：IEEE，2022：1280-1289.
17. [17] GE Y Y，SONG Y B，ZHANG R M，et al. Parser-free Virtual Try-on via Distilling Appearance Flows [C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Nashville：IEEE，2021：8481-8489.

作者简介

陈相宜（2002.04—），女，汉族，四川射洪人，硕士在读，研究方向：深度学习、图像处理。