VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization

Choi, Seung-Hwan; Park, Sunghyun; Lee, Minsoo; Choo, Jaegul

doi:10.1109/cvpr46437.2021.01391

Cited by 117 publications

(103 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…M3D-VTON highlights the first attempt to bridge the 2D try-on and 3D human reconstruction, leading to a effective solution of 3D try-on problem in a novel view. Some of the other promising works for AR shopping for clothing includes, SwapNet [21], Learning-based animation of clothing for virtual try-on [22], GarNet: A two-stream network for fast and accurate 3d cloth draping [23], 360degree textures of people in clothing from a single image [24], M2e-try on net: Fashion from model to everyone [25], Fw-gan: Flow-navigated warping gan for video virtual tryon [26], LA-VITON: a network for looking-attractive virtual try-on [27], Fashion++: Minimal edits for outfit improvement [28], TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style [29], ViBE: Dressing for diverse body shapes [30], Cloth Interactive Transformer for Virtual Try-On [31], VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization [32], Parser-Free Virtual Try-on via Distilling Appearance Flows [33], and Complementary Transfering Network (CT-Net) [34].…”

Section: A Models For Clothing Shopping and Try Onmentioning

confidence: 99%

Modern Augmented Reality: Applications, Trends, and Future Directions

Minaee¹,

Liang²,

Yan³

2022

Preprint

View full text Add to dashboard Cite

Augmented reality (AR) is one of the relatively old, yet trending areas in the intersection of computer vision and computer graphics with numerous applications in several areas, from gaming and entertainment, to education and healthcare.Although it has been around for nearly fifty years, it has seen a lot of interest by the research community in the recent years, mainly because of the huge success of deep learning models for various computer vision and AR applications, which made creating new generations of AR technologies possible. This work tries to provide an overview of modern augmented reality, from both application-level and technical perspective. We first give an overview of main AR applications, grouped into more than ten categories. We then give an overview of around 100 recent promising machine learning based works developed for AR systems, such as deep learning works for AR shopping (clothing, makeup), AR based image filters (such as Snapchat's lenses), AR animations, and more. In the end we discuss about some of the current challenges in AR domain, and the future directions in this area.

show abstract

Section: A Models For Clothing Shopping and Try Onmentioning

confidence: 99%

Modern Augmented Reality: Applications, Trends, and Future Directions

Minaee¹,

Liang²,

Yan³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Due to the great application potential, research on 2D garment transfer has been explored intensively [1,4,6,9,10,22,31,32,43,46]. VITON [13] and CP-VTON [42] are the starting point in this convincing field.…”

Section: Image-based Garment Transfermentioning

confidence: 99%

Dressing in the Wild by Watching Dance Videos

Dong¹,

Zhao²,

Xie³

et al. 2022

Preprint

View full text Add to dashboard Cite

“…If so, is it based on Pytorch library? We explored a myriad of studies Han et al [2018], Raj et al [2018], Yang and Lin [2021], Raffiee and Sollami [2021], Choi et al [2021], Yang et al [2020], Jong and Moh [2019], and these did not qualify the criteria mentioned above. The datasets that were open to the public were VITON Han et al [2018] and DeepFashion Liu et al [2016].…”

Section: Baseline Selectionmentioning

confidence: 99%

Controllable Garment Transfer

Son¹,

Cabezon²,

Siga³

et al. 2022

Preprint

View full text Add to dashboard Cite

Image-based garment transfer replaces the garment on the target human with the desired garment; this enables users to virtually view themselves in the desired garment. To this end, many approaches have been proposed using the generative model and have shown promising results. However, most fail to provide the user with on the fly garment modification functionality. We aim to add this customizable option of "garment tweaking" to our model to control garment attributes, such as sleeve length, waist width, and garment texture.Preprint. Under review.

show abstract

VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization

Cited by 117 publications

References 20 publications

Modern Augmented Reality: Applications, Trends, and Future Directions

Modern Augmented Reality: Applications, Trends, and Future Directions

Dressing in the Wild by Watching Dance Videos

Controllable Garment Transfer

Contact Info

Product

Resources

About