The objective of image-based virtual try-on is to seamlessly integrate clothing onto a target image, generating a realistic representation of the character in the specified attire. However, existing virtual try-on met...The objective of image-based virtual try-on is to seamlessly integrate clothing onto a target image, generating a realistic representation of the character in the specified attire. However, existing virtual try-on methods frequently encounter challenges, including misalignment between the body and clothing, noticeable artifacts, and the loss of intricate garment details. To overcome these challenges, we introduce a two-stage high-resolution virtual try-on framework that integrates an attention mechanism, comprising a garment warping stage and an image generation stage. During the garment warping stage, we incorporate a channel attention mechanism to effectively retain the critical features of the garment, addressing challenges such as the loss of patterns, colors, and other essential details commonly observed in virtual try-on images produced by existing methods. During the image generation stage, with the aim of maximizing the utilization of the information proffered by the input image, the input features undergo double sampling within the normalization procedure, thereby enhancing the detail fidelity and clothing alignment efficacy of the output image. Experimental evaluations conducted on high-resolution datasets validate the effectiveness of the proposed method. Results demonstrate significant improvements in preserving garment details, reducing artifacts, and achieving superior alignment between the clothing and body compared to baseline methods, establishing its advantage in generating realistic and high-quality virtual try-on images.展开更多
Improving customer experience has become a more and more important role in enhancing customer service in fashion retailing business. In this study, a kind of intelligent garment coordination and try-on system for fash...Improving customer experience has become a more and more important role in enhancing customer service in fashion retailing business. In this study, a kind of intelligent garment coordination and try-on system for fashion retailing was proposed. Radio Frequency Identification （RFID） technology was used to identify customer and garment item automatically. The intelligent procedure for garment coordination recommendation using Artificial Neural Network （ANN） was developed to imitate fashion designers＇ decision-making on garment coordination. Virtual try-on algorithm based on the customer＇s 2D/mago was accomplished using imagewarping technique. The system architecture and the software framework were also described. The results show that the ＇system is a practical and useful application for fashion retailers.展开更多
Digital try-on systems for e-commerce have the potential to change people’s lives and provide notable economic benefits.However,their development is limited by practical constraints,such as accurate sizing of the bod...Digital try-on systems for e-commerce have the potential to change people’s lives and provide notable economic benefits.However,their development is limited by practical constraints,such as accurate sizing of the body and realism of demonstrations.We enumerate three open challenges remaining for a complete and easy-to-use try-on system that recent advances in machine learning make increasingly tractable.For each,we describe the problem,introduce state-of-the-art approaches,and provide future directions.展开更多
A virtual cosmetics try-on system provides a realistic try-on experience for consumers and helps them efficiently choose suitable cosmetics.In this article,we propose a real-time augmented reality virtual cosmetics tr...A virtual cosmetics try-on system provides a realistic try-on experience for consumers and helps them efficiently choose suitable cosmetics.In this article,we propose a real-time augmented reality virtual cosmetics try-on system for smartphones(ARCosmetics),taking speed,accuracy,and stability into consideration at each step to ensure a better user experience.A novel and very fast face tracking method utilizes the face detection box and the average position of facial landmarks to estimate the faces in continuous frames.A dynamic weight Wing loss is introduced to assign a dynamic weight to every landmark by the estimated error during training.It balances the attention between small,medium,and large range error and thus increases the accuracy and robustness.We also designed a weighted average method to utilize the information of the adjacent frame for landmark refinement,guaranteeing the stability of the generated landmarks.Extensive experiments conducted on a large 106-point facial landmark dataset and the 300-VW dataset demonstrate the superior performance of the proposed method compared to other state-of-the-art methods.We also conducted user satisfaction studies further to verify the efficiency and effectiveness of our ARCosmetics system.展开更多
Image-based virtual try-on systems have significant commercial value in online garment shopping.However,prior methods fail to appropriately handle details,so are defective in maintaining the original appearance of org...Image-based virtual try-on systems have significant commercial value in online garment shopping.However,prior methods fail to appropriately handle details,so are defective in maintaining the original appearance of organizational items including arms,the neck,and in-shop garments.We propose a novel high fidelity virtual try-on network to generate realistic results.Specifically,a distributed pipeline is used for simultaneous generation of organizational items.First,the in-shop garment is warped using thin plate splines(TPS)to give a coarse shape reference,and then a corresponding target semantic map is generated,which can adaptively respond to the distribution of different items triggered by different garments.Second,organizational items are componentized separately using our novel semantic map-based image adjustment network(SMIAN)to avoid interference between body parts.Finally,all components are integrated to generatethe overall result by SMIAN.A priori dual-modalinformation is incorporated in the tail layers of SMIAN to improve the convergence rate of the network.Experiments demonstrate that the proposed method can retain better details of condition information than current methods.Our method achieves convincing quantitative and qualitative results on existing benchmark datasets.展开更多
This study proposes a real time 3D virtual model controll and a virtual dressing room application to enable users to try virtual garments and shoes on in front of a virtual mirror. A virtual representation of the user...This study proposes a real time 3D virtual model controll and a virtual dressing room application to enable users to try virtual garments and shoes on in front of a virtual mirror. A virtual representation of the user appears in a virtual changing room and the user＇s hand motions select the clothes from a list on the screen. Afterwards, the selected virtual clothes appear on a humanoid model in the virtual mirror. For the purpose of aligning the 3D garments and shoes with the model, 3D locations of the joints are used for positioning, scaling and rotating. By using our developed algorithm, small, medium, large or xlarge garment size is selected automatically and this information is shown on the screen. Then, we apply skin color detection to handle the unwanted occlusions between the user and the model. To create a more realistic effect, the system takes into account different images of the clothes according to different human poses and movements. Optional mirror selection buttons make it possible to have multiple viewing angles on the model. Additionally, we developed an algorithm for matching up all motions between the model and garments. In this study, we benefit from the Microsoft Kinect SDK （software development kit） in order to follow the user＇s movements, coordinate the suitable clothe try-ons and provide depth sort effect to the human body and clothes. In order to use the rapid calculation attributes of game engines, we used unity 3D game engine.展开更多
Current image-editing tools do not match up to the demands of personalized image manipulation,one application of which is changing clothes in usercaptured images. Previous work can change single color clothes using pa...Current image-editing tools do not match up to the demands of personalized image manipulation,one application of which is changing clothes in usercaptured images. Previous work can change single color clothes using parametric human warping methods.In this paper, we propose an image-based clothes changing system, exploiting body factor extraction and content-aware image warping. Image segmentation and mask generation are first applied to the user input.Afterwards, we determine joint positions via a neural network. Then, body shape matching is performed and the shape of the model is warped to the user's shape. Finally, head swapping is performed to produce realistic virtual results. We also provide a supervision and labeling tool for refinement and further assistance when creating a dataset.展开更多
基金supported by the National Natural Science Foundation of China(61772179)Hunan Provincial Natural Science Foundation of China(2022JJ50016,2023JJ50095)+1 种基金the Science and Technology Plan Project of Hunan Province(2016TP1020)Double First-Class University Project of Hunan Province(Xiangjiaotong[2018]469,[2020]248).
文摘The objective of image-based virtual try-on is to seamlessly integrate clothing onto a target image, generating a realistic representation of the character in the specified attire. However, existing virtual try-on methods frequently encounter challenges, including misalignment between the body and clothing, noticeable artifacts, and the loss of intricate garment details. To overcome these challenges, we introduce a two-stage high-resolution virtual try-on framework that integrates an attention mechanism, comprising a garment warping stage and an image generation stage. During the garment warping stage, we incorporate a channel attention mechanism to effectively retain the critical features of the garment, addressing challenges such as the loss of patterns, colors, and other essential details commonly observed in virtual try-on images produced by existing methods. During the image generation stage, with the aim of maximizing the utilization of the information proffered by the input image, the input features undergo double sampling within the normalization procedure, thereby enhancing the detail fidelity and clothing alignment efficacy of the output image. Experimental evaluations conducted on high-resolution datasets validate the effectiveness of the proposed method. Results demonstrate significant improvements in preserving garment details, reducing artifacts, and achieving superior alignment between the clothing and body compared to baseline methods, establishing its advantage in generating realistic and high-quality virtual try-on images.
基金National Nature Science Foundations of China (No.60975059, No.60775052)Specialized Research Fund for the Doctoral Program of Higher Education from Ministry of Education of China (No.20090075110002)Projects of Shanghai Committee of Science and Technology, China (No.09JC1400900, No.08JC1400100, No.10DZ0506500)
文摘Improving customer experience has become a more and more important role in enhancing customer service in fashion retailing business. In this study, a kind of intelligent garment coordination and try-on system for fashion retailing was proposed. Radio Frequency Identification （RFID） technology was used to identify customer and garment item automatically. The intelligent procedure for garment coordination recommendation using Artificial Neural Network （ANN） was developed to imitate fashion designers＇ decision-making on garment coordination. Virtual try-on algorithm based on the customer＇s 2D/mago was accomplished using imagewarping technique. The system architecture and the software framework were also described. The results show that the ＇system is a practical and useful application for fashion retailers.
基金This research was supported in part by the Iribe Professorship and the National Science Foundation.
文摘Digital try-on systems for e-commerce have the potential to change people’s lives and provide notable economic benefits.However,their development is limited by practical constraints,such as accurate sizing of the body and realism of demonstrations.We enumerate three open challenges remaining for a complete and easy-to-use try-on system that recent advances in machine learning make increasingly tractable.For each,we describe the problem,introduce state-of-the-art approaches,and provide future directions.
基金supported in part by the National Key R&D Program of China(2021ZD0140407)in part by the National Natural Science Foundation of China(Grant No.U21A20523).
文摘A virtual cosmetics try-on system provides a realistic try-on experience for consumers and helps them efficiently choose suitable cosmetics.In this article,we propose a real-time augmented reality virtual cosmetics try-on system for smartphones(ARCosmetics),taking speed,accuracy,and stability into consideration at each step to ensure a better user experience.A novel and very fast face tracking method utilizes the face detection box and the average position of facial landmarks to estimate the faces in continuous frames.A dynamic weight Wing loss is introduced to assign a dynamic weight to every landmark by the estimated error during training.It balances the attention between small,medium,and large range error and thus increases the accuracy and robustness.We also designed a weighted average method to utilize the information of the adjacent frame for landmark refinement,guaranteeing the stability of the generated landmarks.Extensive experiments conducted on a large 106-point facial landmark dataset and the 300-VW dataset demonstrate the superior performance of the proposed method compared to other state-of-the-art methods.We also conducted user satisfaction studies further to verify the efficiency and effectiveness of our ARCosmetics system.
基金supported by Young Talents Programme of Scientific Research Program of Hubei Education Department(Project No.Q20201709)Research on the Key Technology of Flexible Intelligent Manufacturing of Clothing based on Digital Twin of Hubei Key Research and Development Program(Project No.2021BAA042)Open Topic of Engineering Research Center of Hubei Province for Clothing Information(Project No.900204).
文摘Image-based virtual try-on systems have significant commercial value in online garment shopping.However,prior methods fail to appropriately handle details,so are defective in maintaining the original appearance of organizational items including arms,the neck,and in-shop garments.We propose a novel high fidelity virtual try-on network to generate realistic results.Specifically,a distributed pipeline is used for simultaneous generation of organizational items.First,the in-shop garment is warped using thin plate splines(TPS)to give a coarse shape reference,and then a corresponding target semantic map is generated,which can adaptively respond to the distribution of different items triggered by different garments.Second,organizational items are componentized separately using our novel semantic map-based image adjustment network(SMIAN)to avoid interference between body parts.Finally,all components are integrated to generatethe overall result by SMIAN.A priori dual-modalinformation is incorporated in the tail layers of SMIAN to improve the convergence rate of the network.Experiments demonstrate that the proposed method can retain better details of condition information than current methods.Our method achieves convincing quantitative and qualitative results on existing benchmark datasets.
文摘This study proposes a real time 3D virtual model controll and a virtual dressing room application to enable users to try virtual garments and shoes on in front of a virtual mirror. A virtual representation of the user appears in a virtual changing room and the user＇s hand motions select the clothes from a list on the screen. Afterwards, the selected virtual clothes appear on a humanoid model in the virtual mirror. For the purpose of aligning the 3D garments and shoes with the model, 3D locations of the joints are used for positioning, scaling and rotating. By using our developed algorithm, small, medium, large or xlarge garment size is selected automatically and this information is shown on the screen. Then, we apply skin color detection to handle the unwanted occlusions between the user and the model. To create a more realistic effect, the system takes into account different images of the clothes according to different human poses and movements. Optional mirror selection buttons make it possible to have multiple viewing angles on the model. Additionally, we developed an algorithm for matching up all motions between the model and garments. In this study, we benefit from the Microsoft Kinect SDK （software development kit） in order to follow the user＇s movements, coordinate the suitable clothe try-ons and provide depth sort effect to the human body and clothes. In order to use the rapid calculation attributes of game engines, we used unity 3D game engine.
基金supported by the National Natural Science Foundation of China (Project No. 61521002)Research Grant of Beijing Higher Institution Engineering Research Center
文摘Current image-editing tools do not match up to the demands of personalized image manipulation,one application of which is changing clothes in usercaptured images. Previous work can change single color clothes using parametric human warping methods.In this paper, we propose an image-based clothes changing system, exploiting body factor extraction and content-aware image warping. Image segmentation and mask generation are first applied to the user input.Afterwards, we determine joint positions via a neural network. Then, body shape matching is performed and the shape of the model is warped to the user's shape. Finally, head swapping is performed to produce realistic virtual results. We also provide a supervision and labeling tool for refinement and further assistance when creating a dataset.
