Improving Fashion Landmark Detection by Dual Attention Feature Enhancement

Chen, Ming; Qin, Yingjie; Qi, Lizhe; Sun, Yunquan

doi:10.1109/iccvw.2019.00374

Cited by 25 publications

(14 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Hourglass 512×512 model was trained for 100 epochs with a batch size = 46 images. Learning rate schedule: 1e-3 -65 epochs, 4e-4 -20 epochs, 4e-5 -15 Approach mAP pt mAP box Mask R-CNN [2] 0.529 0.638 DeepMark [8] 0.532 0.723 DAFE [1] 0.549 -Hourglass 512×512 0.583 0.735 Hourglass 768×768 0.591 0.737 epochs. Hourglass 768×768 model was fine-tuned from Hourglass 512×512 for 25 epochs with a batch size = 22 images: 2e-5 -20 epochs, 1e-5 -5 epochs.…”

Section: Resultsmentioning

confidence: 99%

DeepMark: One-Shot Clothing Detection

Sidnev¹,

Trushkov²,

Kazakov³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 99%

DeepMark: One-Shot Clothing Detection

Sidnev¹,

Trushkov²,

Kazakov³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

show abstract

“…Prior work estimates the shape of the human body [3,30], clothing items [10,27] and both [40,47], through 2D images. The DensePose [1] descriptor helps model the deformation and shading of clothes and has been adopted by recent work [42,14,56,62,7,61].…”

Section: Related Workmentioning

confidence: 99%

Toward Accurate and Realistic Outfits Visualization with Attention to Details

Li¹,

Chong²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Virtual try-on methods aim to generate images of fashion models wearing arbitrary combinations of garments. This is a challenging task because the generated image must appear realistic and accurately display the interaction between garments. Prior works produce images that are filled with artifacts and fail to capture important visual details necessary for commercial applications. We propose Outfit Visualization Net (OVNet) to capture these important details (e.g. buttons, shading, textures, realistic hemlines, and interactions between garments) and produce high quality multiple-garment virtual try-on images. OVNet consists of 1) a semantic layout generator and 2) an image generation pipeline using multiple coordinated warps. We train the warper to output multiple warps using a cascade loss, which refines each successive warp to focus on poorly generated regions of a previous warp and yields consistent improvements in detail. In addition, we introduce a method for matching outfits with the most suitable model and produce significant improvements for both our and other previous try-on methods. Through quantitative and qualitative analysis, we demonstrate our method generates substantially higher-quality studio images compared to prior works for multi-garment outfits. An interactive interface powered by this method has been deployed on fashion e-commerce websites and received overwhelmingly positive feedback.

show abstract

“…Prior work estimated the shape of human body [4,27], clothing items [10,25] and both [35,40], through 2D images. The DensePose [1] descriptor helps modeling the deformation and shading of cloth and, therefore, has been adopted by recent work [36,13,47,51,7,52].…”

Section: Related Workmentioning

confidence: 99%

“…MG-VTON [12] further refine the generation method using a three-stage generation network. Other work [21,55,51,7,46] followed similar procedure. Han et al [15] argued that TPS transformation has low degree of freedom and proposed a flow-based method to create the warp.…”

Section: Related Workmentioning

confidence: 99%

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

Improving Fashion Landmark Detection by Dual Attention Feature Enhancement

Cited by 25 publications

References 13 publications

DeepMark: One-Shot Clothing Detection

DeepMark: One-Shot Clothing Detection

Toward Accurate and Realistic Outfits Visualization with Attention to Details

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

Contact Info

Product

Resources

About