Dress Code: High-Resolution Multi-category Virtual Try-On

Morelli, Davide; Fincato, Matteo; Cornia, Marcella; Landi, Federico; Cesari, Fabio; Cucchiara, Rita

doi:10.1007/978-3-031-20074-8_20

Cited by 11 publications

(14 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the context of the virtual try-on task, we employ two widely-used, publicly available high-resolution datasets for virtual try-on: VITON-HD [14] and Dress Code [41]. We keep the same train-test split as the previous methods [29,40] on both of these datasets. In our study, we only use the official datasets for training the virtual try-on tasks to ensure fairness.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Impact of user-generated travel posts on travel decisions: A comparative study on Weibo and Xiaohongshu

Wang

Huang²,

Liu-Lastres³

2022

Annals of Tourism Research Empirical Insights

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

“…Virtual Try-on. Virtual try-on approaches can be categorized into 3D-based [7,21,30,38] and image-based methods [9,17,22,23,28,29,32,40,41,51]. Imagebased methods are more promising because of their lightweight nature and the ability to generate reasonable results using large-scale try-on datasets.…”

Section: Related Workmentioning

confidence: 99%

Impact of user-generated travel posts on travel decisions: A comparative study on Weibo and Xiaohongshu

Wang

Huang²,

Liu-Lastres³

2022

Annals of Tourism Research Empirical Insights

View full text Add to dashboard Cite

“…SAL-VTON [77] makes improvements based on HR-Net [79] and proposes a Landmark estimation network. To train this network, a open source landmark dataset has been annotated on three mainstream datasets: VITON [21], VITON-HD [39], and Dress-Code [80]. The landmark shown in the Fig.…”

Section: Cloth-agnostic Person Representationmentioning

confidence: 99%

“…Dress Code dataset was proposed by Morelli et al in 2022 [80], which is more than three times larger than the publicly available virtual try-on datasets, with highresolution paired images (1024 × 768). Different from VI-TON, which only contains upper-body female image pairs, Dress Code contains upper-body, lower-body, and full-body clothing for both female and male, as well as corresponding model try-on images.…”

Section: Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

Monocular Image-Based 3-D Model Retrieval: A Benchmark

Song

Nie

et al. 2022

IEEE Trans. Cybern.

View full text Add to dashboard Cite

Image-based virtual try-on aims to synthesize a naturally dressed person image with a clothing image, which revolutionizes online shopping and inspires related topics within image generation, showing both research significance and commercial potential. However, there is a big gap between current research progress and commercial applications and an absence of comprehensive overview of this field to accelerate the development. In this survey, we provide a comprehensive analysis of the state-of-the-art techniques and methodologies in aspects of pipeline architecture, person representation and key modules such as try-on indication, clothing warping and try-on stage. We propose a new semantic criteria with CLIP, and evaluate representative methods with uniformly implemented evaluation metrics on the same dataset. In addition to quantitative and qualitative evaluation of current open-source methods, we also utilize ControlNet to fine-tune a recent large image generation model (PBE) to show future potential of large-scale models on imagebased virtual try-on task. Finally, unresolved issues are highlighted and future research directions are prospected to identify key trends and inspire further exploration. The uniformly implemented evaluation metrics, dataset and collected methods will be made public available at https://github.com/little-misfit/Survey-Of-Virtual-Try-On.

show abstract