The Experts below are selected from a list of 114 Experts worldwide ranked by ideXlab platform

Gerard Ponsmoll - One of the best experts on this subject based on the ideXlab platform.

  • Sizer a dataset and model for parsing 3d Clothing and learning Size sensitive 3d Clothing
    European Conference on Computer Vision, 2020
    Co-Authors: Garvita Tiwari, Bharat Lal Bhatnagar, Tony Tung, Gerard Ponsmoll
    Abstract:

    While models of 3D Clothing learned from real data exist, no method can predict Clothing deformation as a function of garment Size. In this paper, we introduce SizerNet to predict 3D Clothing conditioned on human body shape and garment Size parameters, and ParserNet to infer garment meshes and shape under Clothing with personal details in a single pass from an input mesh. SizerNet allows to estimate and visualize the dressing effect of a garment in various Sizes, and ParserNet allows to edit Clothing of an input mesh directly, removing the need for scan segmentation, which is a challenging problem in itself. To learn these models, we introduce the SizeR dataset of Clothing Size variation which includes 100 different subjects wearing casual Clothing items in various Sizes, totaling to approximately 2000 scans. This dataset includes the scans, registrations to the SMPL model, scans segmented in Clothing parts, garment category and Size labels. Our experiments show better parsing accuracy and Size prediction than baseline methods trained on SizeR. The code, model and dataset will be released for research purposes at: https://virtualhumans.mpi-inf.mpg.de/Sizer/.

  • Sizer a dataset and model for parsing 3d Clothing and learning Size sensitive 3d Clothing
    arXiv: Computer Vision and Pattern Recognition, 2020
    Co-Authors: Garvita Tiwari, Bharat Lal Bhatnagar, Tony Tung, Gerard Ponsmoll
    Abstract:

    While models of 3D Clothing learned from real data exist, no method can predict Clothing deformation as a function of garment Size. In this paper, we introduce SizerNet to predict 3D Clothing conditioned on human body shape and garment Size parameters, and ParserNet to infer garment meshes and shape under Clothing with personal details in a single pass from an input mesh. SizerNet allows to estimate and visualize the dressing effect of a garment in various Sizes, and ParserNet allows to edit Clothing of an input mesh directly, removing the need for scan segmentation, which is a challenging problem in itself. To learn these models, we introduce the SizeR dataset of Clothing Size variation which includes $100$ different subjects wearing casual Clothing items in various Sizes, totaling to approximately 2000 scans. This dataset includes the scans, registrations to the SMPL model, scans segmented in Clothing parts, garment category and Size labels. Our experiments show better parsing accuracy and Size prediction than baseline methods trained on SizeR. The code, model and dataset will be released for research purposes.

Angkoso, Cucun Very - One of the best experts on this subject based on the ideXlab platform.

  • Implementasi Metode Euclidean Distance untuk Rekomendasi Ukuran Pakaian pada Aplikasi Ruang Ganti Virtual
    'Fakultas Ilmu Komputer Universitas Brawijaya', 2018
    Co-Authors: Rizaldi Rezky, Kurniawati Arik, Angkoso, Cucun Very
    Abstract:

    Perkembangan jual beli garmen secara online, dihadapkan pada kenyataan adanya 70% pengembalian produk oleh pembeli, akibat ketidaksesuaian antara harapan dan kenyataan model serta ukuran garmen. Kehadiran virtual fitting room secara online, diharapkan mampu mengurangi adanya pengembalian produk, memberikan pengaruh positif terhadap keistimewaan suatu produk, keinginan untuk membeli dan kepastian membeli secara online. Virtual Fitting Room ini bisa diimplementasikan pada toko online ataupun toko baju seperti biasa. Tahapan penelitian meliputi : penerapan teknologi kinect untuk mendapatkan data skeleton dari calon pembeli yang digunakan sebagai dasar untuk memberikan rekomendasi ukuran pakaian, selanjutnya perhitungan euclidean distance digunakan untuk menghitung ukuran punggung calon pembeli dan terakhir penerapan teknologi augmented reality untuk menampilkan pakaian virtual 3 dimensi yang melekat tepat di badan calon pembeli. Sistem rekomendasi ini mampu menampilkan calon pembeli dengan menggunakan baju virtual 3 dimensi yang sesuai dengan ukuran rekomendasi dari sistem (S,M,L, atau XL). Sistem ini juga memberikan fitur bagi calon pembeli untuk mencoba model pakaian lainnya. Sistem dapat memperlihatkan baju virtual 3 dimensi yang tetap melekat pada badan calon pembeli, ketika melakukan rotasi ke kanan 900, ke kiri 900, balik kanan 1800 dan balik kiri 1800. Hasil uji coba sistem rekomendasi ukuran pakaian ini akan berjalan secara optimal jika pengaturan ketinggian kinect sebesar 55 cm dari tanah. Untuk ketinggian kinect 55cm, 65cm dan 75 cm dari tanah, sistem ini mampu menyajikan kesesuaian rekomendasi ukuran dibandingkan dengan ukuran asli dari calon pembeli sebesar 70%. Kata kunci: kinect, augmented reality, euclidean distance, virtual fitting room  AbstractThe development of online garment sale, faced with the fact that there is 70% return of product by the buyer, due to a mismatch between expectation and reality of model and garment Size. The presence of virtual fitting room in the online store is expected to reduce the return of products, give a positive influence on the privilege of a product, the desire to buy and certainty to buy online. Virtual Fitting Room can be implemented in the online store or Clothing store as usual. The research stages include the application of Kinect technology to obtain skeleton data from prospective buyers used as a basis for providing system recommendations, then euclidean distance calculation is used to calculate the Size back potential buyers, and lastly application of augmented reality technology to display the right three-dimensional virtual Clothing in potential buyer body. This recommendation system can present potential buyers by using 3-dimensional virtual shirts attached to their bodies by the recommended Size of the system (S, M, L, or XL). This system also provides features for potential buyers to try other Clothing models. The system can show a 3-dimensional virtual shirt that remains attached to the body of potential buyers, while rotating right 900, left 900, right turn 1800 and left turn 1800. The test results of this Clothing Size recommendation system will run optimally if the Kinect height setting of 55 cm from the ground. For the Kinect height of 55cm, 65cm and 75cm from the ground, the system can present the recommended Size with the original Size of the potential buyer of 70%. Keywords: kinect, augmented reality, euclidean distance, virtual fitting roomPerkembangan jual beli garmen secara online, dihadapkan pada kenyataan adanya 70% pengembalian produk oleh pembeli, akibat ketidaksesuaian antara harapan dan kenyataan model serta ukuran garmen. Kehadiran virtual fitting room secara online, diharapkan mampu mengurangi adanya pengembalian produk, memberikan pengaruh positif terhadap keistimewaan suatu produk, keinginan untuk membeli dan kepastian membeli secara online. Virtual Fitting Room ini bisa diimplementasikan pada toko online ataupun toko baju seperti biasa. Tahapan penelitian meliputi : penerapan teknologi kinect untuk mendapatkan data skeleton dari calon pembeli yang digunakan sebagai dasar untuk memberikan rekomendasi ukuran pakaian, selanjutnya perhitungan euclidean distance digunakan untuk menghitung ukuran punggung calon pembeli dan terakhir penerapan teknologi augmented reality untuk menampilkan pakaian virtual 3 dimensi yang melekat tepat di badan calon pembeli. Sistem rekomendasi ini mampu menampilkan calon pembeli dengan menggunakan baju virtual 3 dimensi yang sesuai dengan ukuran rekomendasi dari sistem (S,M,L, atau XL). Sistem ini juga memberikan fitur bagi calon pembeli untuk mencoba model pakaian lainnya. Sistem dapat memperlihatkan baju virtual 3 dimensi yang tetap melekat pada badan calon pembeli, ketika melakukan rotasi ke kanan 900, ke kiri 900, balik kanan 1800 dan balik kiri 1800. Hasil uji coba sistem rekomendasi ukuran pakaian ini akan berjalan secara optimal jika pengaturan ketinggian kinect sebesar 55 cm dari tanah. Untuk ketinggian kinect 55cm, 65cm dan 75 cm dari tanah, sistem ini mampu menyajikan kesesuaian rekomendasi ukuran dibandingkan dengan ukuran asli dari calon pembeli sebesar 70%. AbstractThe development of online garment sale, faced with the fact that there is 70% return of product by the buyer, due to a mismatch between expectation and reality of model and garment Size. The presence of virtual fitting room in the online store is expected to reduce the return of products, give a positive influence on the privilege of a product, the desire to buy and certainty to buy online. Virtual Fitting Room can be implemented in the online store or Clothing store as usual. The research stages include the application of Kinect technology to obtain skeleton data from prospective buyers used as a basis for providing system recommendations, then euclidean distance calculation is used to calculate the Size back potential buyers, and lastly application of augmented reality technology to display the right three-dimensional virtual Clothing in potential buyer body. This recommendation system can present potential buyers by using 3-dimensional virtual shirts attached to their bodies by the recommended Size of the system (S, M, L, or XL). This system also provides features for potential buyers to try other Clothing models. The system can show a 3-dimensional virtual shirt that remains attached to the body of potential buyers, while rotating right 900, left 900, right turn 1800 and left turn 1800. The test results of this Clothing Size recommendation system will run optimally if the Kinect height setting of 55 cm from the ground. For the Kinect height of 55cm, 65cm and 75cm from the ground, the system can present the recommended Size with the original Size of the potential buyer of 70%.

Cucun Very Angkoso - One of the best experts on this subject based on the ideXlab platform.

  • Implementasi Metode Euclidean Distance untuk Rekomendasi Ukuran Pakaian pada Aplikasi Ruang Ganti Virtual
    University of Brawijaya, 2018
    Co-Authors: Rezky Rizaldi, Arik Kurniawati, Cucun Very Angkoso
    Abstract:

    Perkembangan jual beli garmen secara online, dihadapkan pada kenyataan adanya 70% pengembalian produk oleh pembeli, akibat ketidaksesuaian antara harapan dan kenyataan model serta ukuran garmen. Kehadiran virtual fitting room secara online, diharapkan mampu mengurangi adanya pengembalian produk, memberikan pengaruh positif terhadap keistimewaan suatu produk, keinginan untuk membeli dan kepastian membeli secara online. Virtual Fitting Room ini bisa diimplementasikan pada toko online ataupun toko baju seperti biasa. Tahapan penelitian meliputi : penerapan teknologi kinect untuk mendapatkan data skeleton dari calon pembeli yang digunakan sebagai dasar untuk memberikan rekomendasi ukuran pakaian, selanjutnya perhitungan euclidean distance digunakan untuk menghitung ukuran punggung calon pembeli dan terakhir penerapan teknologi augmented reality untuk menampilkan pakaian virtual 3 dimensi yang melekat tepat di badan calon pembeli. Sistem rekomendasi ini mampu menampilkan calon pembeli dengan menggunakan baju virtual 3 dimensi yang sesuai dengan ukuran rekomendasi dari sistem (S,M,L, atau XL). Sistem ini juga memberikan fitur bagi calon pembeli untuk mencoba model pakaian lainnya. Sistem dapat memperlihatkan baju virtual 3 dimensi yang tetap melekat pada badan calon pembeli, ketika melakukan rotasi ke kanan 900, ke kiri 900, balik kanan 1800 dan balik kiri 1800. Hasil uji coba sistem rekomendasi ukuran pakaian ini akan berjalan secara optimal jika pengaturan ketinggian kinect sebesar 55 cm dari tanah. Untuk ketinggian kinect 55cm, 65cm dan 75 cm dari tanah, sistem ini mampu menyajikan kesesuaian rekomendasi ukuran dibandingkan dengan ukuran asli dari calon pembeli sebesar 70%.   Abstract The development of online garment sale, faced with the fact that there is 70% return of product by the buyer, due to a mismatch between expectation and reality of model and garment Size. The presence of virtual fitting room in the online store is expected to reduce the return of products, give a positive influence on the privilege of a product, the desire to buy and certainty to buy online. Virtual Fitting Room can be implemented in the online store or Clothing store as usual. The research stages include the application of Kinect technology to obtain skeleton data from prospective buyers used as a basis for providing system recommendations, then euclidean distance calculation is used to calculate the Size back potential buyers, and lastly application of augmented reality technology to display the right three-dimensional virtual Clothing in potential buyer body. This recommendation system can present potential buyers by using 3-dimensional virtual shirts attached to their bodies by the recommended Size of the system (S, M, L, or XL). This system also provides features for potential buyers to try other Clothing models. The system can show a 3-dimensional virtual shirt that remains attached to the body of potential buyers, while rotating right 900, left 900, right turn 1800 and left turn 1800. The test results of this Clothing Size recommendation system will run optimally if the Kinect height setting of 55 cm from the ground. For the Kinect height of 55cm, 65cm and 75cm from the ground, the system can present the recommended Size with the original Size of the potential buyer of 70%

Garvita Tiwari - One of the best experts on this subject based on the ideXlab platform.

  • Sizer a dataset and model for parsing 3d Clothing and learning Size sensitive 3d Clothing
    European Conference on Computer Vision, 2020
    Co-Authors: Garvita Tiwari, Bharat Lal Bhatnagar, Tony Tung, Gerard Ponsmoll
    Abstract:

    While models of 3D Clothing learned from real data exist, no method can predict Clothing deformation as a function of garment Size. In this paper, we introduce SizerNet to predict 3D Clothing conditioned on human body shape and garment Size parameters, and ParserNet to infer garment meshes and shape under Clothing with personal details in a single pass from an input mesh. SizerNet allows to estimate and visualize the dressing effect of a garment in various Sizes, and ParserNet allows to edit Clothing of an input mesh directly, removing the need for scan segmentation, which is a challenging problem in itself. To learn these models, we introduce the SizeR dataset of Clothing Size variation which includes 100 different subjects wearing casual Clothing items in various Sizes, totaling to approximately 2000 scans. This dataset includes the scans, registrations to the SMPL model, scans segmented in Clothing parts, garment category and Size labels. Our experiments show better parsing accuracy and Size prediction than baseline methods trained on SizeR. The code, model and dataset will be released for research purposes at: https://virtualhumans.mpi-inf.mpg.de/Sizer/.

  • Sizer a dataset and model for parsing 3d Clothing and learning Size sensitive 3d Clothing
    arXiv: Computer Vision and Pattern Recognition, 2020
    Co-Authors: Garvita Tiwari, Bharat Lal Bhatnagar, Tony Tung, Gerard Ponsmoll
    Abstract:

    While models of 3D Clothing learned from real data exist, no method can predict Clothing deformation as a function of garment Size. In this paper, we introduce SizerNet to predict 3D Clothing conditioned on human body shape and garment Size parameters, and ParserNet to infer garment meshes and shape under Clothing with personal details in a single pass from an input mesh. SizerNet allows to estimate and visualize the dressing effect of a garment in various Sizes, and ParserNet allows to edit Clothing of an input mesh directly, removing the need for scan segmentation, which is a challenging problem in itself. To learn these models, we introduce the SizeR dataset of Clothing Size variation which includes $100$ different subjects wearing casual Clothing items in various Sizes, totaling to approximately 2000 scans. This dataset includes the scans, registrations to the SMPL model, scans segmented in Clothing parts, garment category and Size labels. Our experiments show better parsing accuracy and Size prediction than baseline methods trained on SizeR. The code, model and dataset will be released for research purposes.

Kurniawati Arik - One of the best experts on this subject based on the ideXlab platform.

  • Clothing Size recommender on real-time fitting simulation using skeleton tracking and rigging
    'Institute of Research and Community Services Diponegoro University (LPPM UNDIP)', 2020
    Co-Authors: Kurniawati Arik, Kusumaningsih Ari, Aliffio Yanuar
    Abstract:

    Virtual fitting room (VFR) is a technology that replaces conventional fitting rooms. The VFR is not only available in shops, malls, and any shopping center but also in online stores, which makes VFR technology more and more developed, primarily to support online garment sales. VFR become a trending research interest since Microsoft has developed a Kinect tracking system. In this paper, we proposed the interactive 3D virtual fitting room using Microsoft's Kinect tracking and the rigging technique from 3D Modeling Blender and to implement the VFR. VFR manages the progress of virtual fitting that forms the three-dimensional simulations and visualization of garments on virtual counterparts of the real prospective buyer (user). Users can view the Clothing animation on the various poses that are following the user body movements. The system can evaluate the user’s match, guiding them to choose the suitable Size of the clothes using Euclidean distance

  • Implementasi Metode Euclidean Distance untuk Rekomendasi Ukuran Pakaian pada Aplikasi Ruang Ganti Virtual
    'Fakultas Ilmu Komputer Universitas Brawijaya', 2018
    Co-Authors: Rizaldi Rezky, Kurniawati Arik, Angkoso, Cucun Very
    Abstract:

    Perkembangan jual beli garmen secara online, dihadapkan pada kenyataan adanya 70% pengembalian produk oleh pembeli, akibat ketidaksesuaian antara harapan dan kenyataan model serta ukuran garmen. Kehadiran virtual fitting room secara online, diharapkan mampu mengurangi adanya pengembalian produk, memberikan pengaruh positif terhadap keistimewaan suatu produk, keinginan untuk membeli dan kepastian membeli secara online. Virtual Fitting Room ini bisa diimplementasikan pada toko online ataupun toko baju seperti biasa. Tahapan penelitian meliputi : penerapan teknologi kinect untuk mendapatkan data skeleton dari calon pembeli yang digunakan sebagai dasar untuk memberikan rekomendasi ukuran pakaian, selanjutnya perhitungan euclidean distance digunakan untuk menghitung ukuran punggung calon pembeli dan terakhir penerapan teknologi augmented reality untuk menampilkan pakaian virtual 3 dimensi yang melekat tepat di badan calon pembeli. Sistem rekomendasi ini mampu menampilkan calon pembeli dengan menggunakan baju virtual 3 dimensi yang sesuai dengan ukuran rekomendasi dari sistem (S,M,L, atau XL). Sistem ini juga memberikan fitur bagi calon pembeli untuk mencoba model pakaian lainnya. Sistem dapat memperlihatkan baju virtual 3 dimensi yang tetap melekat pada badan calon pembeli, ketika melakukan rotasi ke kanan 900, ke kiri 900, balik kanan 1800 dan balik kiri 1800. Hasil uji coba sistem rekomendasi ukuran pakaian ini akan berjalan secara optimal jika pengaturan ketinggian kinect sebesar 55 cm dari tanah. Untuk ketinggian kinect 55cm, 65cm dan 75 cm dari tanah, sistem ini mampu menyajikan kesesuaian rekomendasi ukuran dibandingkan dengan ukuran asli dari calon pembeli sebesar 70%. Kata kunci: kinect, augmented reality, euclidean distance, virtual fitting room  AbstractThe development of online garment sale, faced with the fact that there is 70% return of product by the buyer, due to a mismatch between expectation and reality of model and garment Size. The presence of virtual fitting room in the online store is expected to reduce the return of products, give a positive influence on the privilege of a product, the desire to buy and certainty to buy online. Virtual Fitting Room can be implemented in the online store or Clothing store as usual. The research stages include the application of Kinect technology to obtain skeleton data from prospective buyers used as a basis for providing system recommendations, then euclidean distance calculation is used to calculate the Size back potential buyers, and lastly application of augmented reality technology to display the right three-dimensional virtual Clothing in potential buyer body. This recommendation system can present potential buyers by using 3-dimensional virtual shirts attached to their bodies by the recommended Size of the system (S, M, L, or XL). This system also provides features for potential buyers to try other Clothing models. The system can show a 3-dimensional virtual shirt that remains attached to the body of potential buyers, while rotating right 900, left 900, right turn 1800 and left turn 1800. The test results of this Clothing Size recommendation system will run optimally if the Kinect height setting of 55 cm from the ground. For the Kinect height of 55cm, 65cm and 75cm from the ground, the system can present the recommended Size with the original Size of the potential buyer of 70%. Keywords: kinect, augmented reality, euclidean distance, virtual fitting roomPerkembangan jual beli garmen secara online, dihadapkan pada kenyataan adanya 70% pengembalian produk oleh pembeli, akibat ketidaksesuaian antara harapan dan kenyataan model serta ukuran garmen. Kehadiran virtual fitting room secara online, diharapkan mampu mengurangi adanya pengembalian produk, memberikan pengaruh positif terhadap keistimewaan suatu produk, keinginan untuk membeli dan kepastian membeli secara online. Virtual Fitting Room ini bisa diimplementasikan pada toko online ataupun toko baju seperti biasa. Tahapan penelitian meliputi : penerapan teknologi kinect untuk mendapatkan data skeleton dari calon pembeli yang digunakan sebagai dasar untuk memberikan rekomendasi ukuran pakaian, selanjutnya perhitungan euclidean distance digunakan untuk menghitung ukuran punggung calon pembeli dan terakhir penerapan teknologi augmented reality untuk menampilkan pakaian virtual 3 dimensi yang melekat tepat di badan calon pembeli. Sistem rekomendasi ini mampu menampilkan calon pembeli dengan menggunakan baju virtual 3 dimensi yang sesuai dengan ukuran rekomendasi dari sistem (S,M,L, atau XL). Sistem ini juga memberikan fitur bagi calon pembeli untuk mencoba model pakaian lainnya. Sistem dapat memperlihatkan baju virtual 3 dimensi yang tetap melekat pada badan calon pembeli, ketika melakukan rotasi ke kanan 900, ke kiri 900, balik kanan 1800 dan balik kiri 1800. Hasil uji coba sistem rekomendasi ukuran pakaian ini akan berjalan secara optimal jika pengaturan ketinggian kinect sebesar 55 cm dari tanah. Untuk ketinggian kinect 55cm, 65cm dan 75 cm dari tanah, sistem ini mampu menyajikan kesesuaian rekomendasi ukuran dibandingkan dengan ukuran asli dari calon pembeli sebesar 70%. AbstractThe development of online garment sale, faced with the fact that there is 70% return of product by the buyer, due to a mismatch between expectation and reality of model and garment Size. The presence of virtual fitting room in the online store is expected to reduce the return of products, give a positive influence on the privilege of a product, the desire to buy and certainty to buy online. Virtual Fitting Room can be implemented in the online store or Clothing store as usual. The research stages include the application of Kinect technology to obtain skeleton data from prospective buyers used as a basis for providing system recommendations, then euclidean distance calculation is used to calculate the Size back potential buyers, and lastly application of augmented reality technology to display the right three-dimensional virtual Clothing in potential buyer body. This recommendation system can present potential buyers by using 3-dimensional virtual shirts attached to their bodies by the recommended Size of the system (S, M, L, or XL). This system also provides features for potential buyers to try other Clothing models. The system can show a 3-dimensional virtual shirt that remains attached to the body of potential buyers, while rotating right 900, left 900, right turn 1800 and left turn 1800. The test results of this Clothing Size recommendation system will run optimally if the Kinect height setting of 55 cm from the ground. For the Kinect height of 55cm, 65cm and 75cm from the ground, the system can present the recommended Size with the original Size of the potential buyer of 70%.