Powering Virtual Try-On via Auxiliary Human Segmentation Learning

Kumar, Ashish; Jandial, Surgan; Chopra, Ayush; Krishnamurthy, Balaji

doi:10.1109/iccvw.2019.00397

Cited by 18 publications

(9 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They train a separate refinement network to combine the warp and the target image. VTNFP [53] extends the work by incorporatiing body segments prediction and later works follow similar procedure [37,24,42,22,2]. However, TPS transformation fails to produce reasonable warps, due to the noisiness of generated masks in our dataset, as shown in Figure 6 right.…”

Section: Related Workmentioning

confidence: 74%

See 1 more Smart Citation

Toward Accurate and Realistic Virtual Try-on Through Shape Matching and Multiple Warps

Li¹,

Chong²,

Liu³

et al. 2020

Preprint

View full text Add to dashboard Cite

A virtual try-on method takes a product image and an image of a model and produces an image of the model wearing the product. Most methods essentially compute warps from the product image to the model image and combine using image generation methods. However, obtaining a realistic image is challenging because the kinematics of garments is complex and because outline, texture, and shading cues in the image reveal errors to human viewers. The garment must have appropriate drapes; texture must be warped to be consistent with the shape of a draped garment; small details (buttons, collars, lapels, pockets, etc.) must be placed appropriately on the garment, and so on. Evaluation is particularly difficult and is usually qualitative. This paper uses quantitative evaluation on a challenging, novel dataset to demonstrate that (a) for any warping method, one can choose target models automatically to improve results, and (b) learning multiple coordinated specialized warpers offers further improvements on results. Target models are chosen by a learned embedding procedure that predicts a representation of the products the model is wearing. This prediction is used to match products to models. Specialized warpers are trained by a method that encourages a second warper to perform well in locations where the first works poorly. The warps are then combined using a U-Net. Qualitative evaluation confirms that these improvements are wholesale over outline, texture shading, and garment details.

show abstract

Section: Related Workmentioning

confidence: 74%

“…The VITON dataset [17] contains pairs of product image (front-view, laying flat, white background) and studio images, 2D pose maps and pose key-points. It has been used by many works [45,11,15,53,24,22,2,37]. Some works [47,15,13,51] on multi-pose matching used DeepFashion [33] or MVC [32] and other self-collected datasets [12,21,47,55].…”

Section: Datasetsmentioning

confidence: 99%

Toward Accurate and Realistic Virtual Try-on Through Shape Matching and Multiple Warps

Li¹,

Chong²,

Liu³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The comparisons of VITON and CP-VTON are given in Figure 6(c). There were several improved works [4,76,210,220] based on CP-VTON. Different from the previous works that needed the in-shop clothing image for virtual try-on, FashionGAN [231] and M2E-TON [195] presented target try-on clothing image based on text description and model image respectively.…”

Section: State-of-the-art Methodsmentioning

confidence: 99%

“…The proposed PGN integrates two twinned subtasks that can be mutually refined under a unified network, i.e., semantic part segmentation, and instance-aware edge detection. Further, Ruan et al [152] proposed CE2P framework 4 containing three key modules, a high-resolution embedding module, a global context embedding module, and an edge perceiving module, for single human parsing. This work won first place within all three human parsing tracks in the seond Look Into Person (LIP) Challenge.…”

Section: 21mentioning

confidence: 99%

Fashion Meets Computer Vision

et al. 2021

View full text Add to dashboard Cite

Fashion is the way we present ourselves to the world and has become one of the world’s largest industries. Fashion, mainly conveyed by vision, has thus attracted much attention from computer vision researchers in recent years. Given the rapid development, this article provides a comprehensive survey of more than 200 major fashion-related works covering four main aspects for enabling intelligent fashion: (1) Fashion detection includes landmark detection, fashion parsing, and item retrieval; (2) Fashion analysis contains attribute recognition, style learning, and popularity prediction; (3) Fashion synthesis involves style transfer, pose transformation, and physical simulation; and (4) Fashion recommendation comprises fashion compatibility, outfit matching, and hairstyle suggestion. For each task, the benchmark datasets and the evaluation protocols are summarized. Furthermore, we highlight promising directions for future research.

show abstract

“…VITON [16] follows the idea of image generation and uses non-parametric geometric transform which makes all the procedure twostage, similar to SwapNet [48] with the difference in the task statement and training data. CP-VTON [56] further improves upon [16] by incorporating a full learnable thin-plate spline transformation, followed by CP-VTON+ [40], LA-VITON [22], Ayush et al [5] and ACGPN [60]. While the above-mentioned works rely on pre-trained human parsers and pose estimators, the recent work of Issenhuth er al.…”

Section: Modeling Clothing Appearancementioning

confidence: 99%

Point-Based Modeling of Human Clothing

Zakharkin¹,

Mazur²,

Grigorev³

et al. 2021

Preprint

View full text Add to dashboard Cite

Figure 1: Our approach models the geometry of diverse clothing outfits using point clouds (bottom row; random point colors). The point clouds are obtained by passing the SMPL meshes (shown in grey) and latent outfit code vectors through a pretrained deep network. Additionally, our approach can model clothing appearance using neural point-based graphics (top row). The outfit appearance can be captured from a video sequence, while a single frame is sufficient for point-based geometric modeling.

show abstract

Powering Virtual Try-On via Auxiliary Human Segmentation Learning

Cited by 18 publications

References 4 publications

Toward Accurate and Realistic Virtual Try-on Through Shape Matching and Multiple Warps

Toward Accurate and Realistic Virtual Try-on Through Shape Matching and Multiple Warps

Fashion Meets Computer Vision

Point-Based Modeling of Human Clothing

Contact Info

Product

Resources

About