The Experts below are selected from a list of 321 Experts worldwide ranked by ideXlab platform

Nicu Sebe - One of the best experts on this subject based on the ideXlab platform.

  • ECCV (25) - XingGAN for Person Image Generation
    Computer Vision – ECCV 2020, 2020
    Co-Authors: Hao Tang, Song Bai, Li Zhang, Philip H. S. Torr, Nicu Sebe
    Abstract:

    We propose a novel Generative Adversarial Network (XingGAN or CrossingGAN) for person Image Generation tasks, i.e., translating the pose of a given person to a desired one. The proposed Xing generator consists of two Generation branches that model the person’s appearance and shape information, respectively. Moreover, we propose two novel blocks to effectively transfer and update the person’s shape and appearance embeddings in a crossing way to mutually improve each other, which has not been considered by any other existing GAN-based Image Generation work. Extensive experiments on two challenging datasets, i.e., Market-1501 and DeepFashion, demonstrate that the proposed XingGAN advances the state-of-the-art performance both in terms of objective quantitative scores and subjective visual realness. The source code and trained models are available at https://github.com/Ha0Tang/XingGAN.

  • XingGAN for Person Image Generation
    arXiv: Computer Vision and Pattern Recognition, 2020
    Co-Authors: Hao Tang, Song Bai, Li Zhang, Philip H. S. Torr, Nicu Sebe
    Abstract:

    We propose a novel Generative Adversarial Network (XingGAN or CrossingGAN) for person Image Generation tasks, i.e., translating the pose of a given person to a desired one. The proposed Xing generator consists of two Generation branches that model the person's appearance and shape information, respectively. Moreover, we propose two novel blocks to effectively transfer and update the person's shape and appearance embeddings in a crossing way to mutually improve each other, which has not been considered by any other existing GAN-based Image Generation work. Extensive experiments on two challenging datasets, i.e., Market-1501 and DeepFashion, demonstrate that the proposed XingGAN advances the state-of-the-art performance both in terms of objective quantitative scores and subjective visual realness. The source code and trained models are available at this https URL.

  • WACV - Attention-based Fusion for Multi-source Human Image Generation
    2020 IEEE Winter Conference on Applications of Computer Vision (WACV), 2020
    Co-Authors: Stéphane Lathuilière, Aliaksandr Siarohin, Enver Sangineto, Nicu Sebe
    Abstract:

    We present a generalization of the person-Image Generation task, in which a human Image is generated conditioned on a target pose and a set X of source appearance Images. In this way, we can exploit multiple, possibly complementary Images of the same person which are usually available at training and at testing time. The solution we propose is mainly based on a local attention mechanism which selects relevant information from different source Image regions, avoiding the necessity to build specific generators for each specific cardinality of X. The empirical evaluation of our method shows the practical interest of addressing the person-Image Generation problem in a multi-source setting.

  • Attention-based Fusion for Multi-source Human Image Generation
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
    Co-Authors: Aliaksandr Siarohin, Stéphane Lathuilière, Enver Sangineto, Nicu Sebe
    Abstract:

    We present a generalization of the person-Image Generation task, in which a human Image is generated conditioned on a target pose and a set X of source appearance Images. In this way, we can exploit multiple, possibly complementary Images of the same person which are usually available at training and at testing time. The solution we propose is mainly based on a local attention mechanism which selects relevant information from different source Image regions, avoiding the necessity to build specific generators for each specific cardinality of X. The empirical evaluation of our method shows the practical interest of addressing the person-Image Generation problem in a multi-source setting.

Luc Van Gool - One of the best experts on this subject based on the ideXlab platform.

  • AAAI - Manifold-valued Image Generation with Wasserstein Generative Adversarial Nets
    Proceedings of the AAAI Conference on Artificial Intelligence, 2019
    Co-Authors: Zhiwu Huang, Luc Van Gool
    Abstract:

    Generative modeling over natural Images is one of the most fundamental machine learning problems. However, few modern generative models, including Wasserstein Generative Adversarial Nets (WGANs), are studied on manifold-valued Images that are frequently encountered in real-world applications. To fill the gap, this paper first formulates the problem of generating manifold-valued Images and exploits three typical instances: hue-saturation-value (HSV) color Image Generation, chromaticity-brightness (CB) color Image Generation, and diffusion-tensor (DT) Image Generation. For the proposed generative modeling problem, we then introduce a theorem of optimal transport to derive a new Wasserstein distance of data distributions on complete manifolds, enabling us to achieve a tractable objective under the WGAN framework. In addition, we recommend three benchmark datasets that are CIFAR-10 HSV/CB color Images, ImageNet HSV/CB color Images, UCL DT Image datasets. On the three datasets, we experimentally demonstrate the proposed manifold-aware WGAN model can generate more plausible manifold-valued Images than its competitors.

  • Manifold-valued Image Generation with Wasserstein Adversarial Networks.
    2017
    Co-Authors: Zhiwu Huang, Luc Van Gool
    Abstract:

    Unsupervised Image Generation has recently received an increasing amount of attention thanks to the great success of generative adversarial networks (GANs), particularly Wasserstein GANs. Inspired by the paradigm of real-valued Image Generation, this paper makes the first attempt to formulate the problem of generating manifold-valued Images, which are frequently encountered in real-world applications. For the study, we specially exploit three typical manifold-valued Image Generation tasks: hue-saturation-value (HSV) color Image Generation, chromaticity-brightness (CB) color Image Generation, and diffusion-tensor (DT) Image Generation. In order to produce such kinds of Images as realistic as possible, we generalize the state-of-the-art technique of Wasserstein GANs to the manifold context with exploiting Riemannian geometry. For the proposed manifold-valued Image Generation problem, we recommend three benchmark datasets that are CIFAR-10 HSV/CB color Images, ImageNet HSV/CB color Images, UCL DT Image datasets. On the three datasets, we experimentally demonstrate the proposed manifold-aware Wasserestein GAN can generate high quality manifold-valued Images.

  • Manifold-valued Image Generation with Wasserstein Generative Adversarial Nets
    arXiv: Computer Vision and Pattern Recognition, 2017
    Co-Authors: Zhiwu Huang, Luc Van Gool
    Abstract:

    Generative modeling over natural Images is one of the most fundamental machine learning problems. However, few modern generative models, including Wasserstein Generative Adversarial Nets (WGANs), are studied on manifold-valued Images that are frequently encountered in real-world applications. To fill the gap, this paper first formulates the problem of generating manifold-valued Images and exploits three typical instances: hue-saturation-value (HSV) color Image Generation, chromaticity-brightness (CB) color Image Generation, and diffusion-tensor (DT) Image Generation. For the proposed generative modeling problem, we then introduce a theorem of optimal transport to derive a new Wasserstein distance of data distributions on complete manifolds, enabling us to achieve a tractable objective under the WGAN framework. In addition, we recommend three benchmark datasets that are CIFAR-10 HSV/CB color Images, ImageNet HSV/CB color Images, UCL DT Image datasets. On the three datasets, we experimentally demonstrate the proposed manifold-aware WGAN model can generate more plausible manifold-valued Images than its competitors.

Changqing Zou - One of the best experts on this subject based on the ideXlab platform.

  • SketchyCOCO: Image Generation from Freehand Scene Sketches.
    arXiv: Computer Vision and Pattern Recognition, 2020
    Co-Authors: Chengying Gao, Qi Liu, Limin Wang, Jianzhuang Liu, Changqing Zou
    Abstract:

    We introduce the first method for automatic Image Generation from scene-level freehand sketches. Our model allows for controllable Image Generation by specifying the synthesis goal via freehand sketches. The key contribution is an attribute vector bridged Generative Adversarial Network called EdgeGAN, which supports high visual-quality object-level Image content Generation without using freehand sketches as training data. We have built a large-scale composite dataset called SketchyCOCO to support and evaluate the solution. We validate our approach on the tasks of both object-level and scene-level Image Generation on SketchyCOCO. Through quantitative, qualitative results, human evaluation and ablation studies, we demonstrate the method's capacity to generate realistic complex scene-level Images from various freehand sketches.

  • CVPR - SketchyCOCO: Image Generation From Freehand Scene Sketches
    2020 IEEE CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020
    Co-Authors: Chengying Gao, Qi Liu, Limin Wang, Jianzhuang Liu, Changqing Zou
    Abstract:

    We introduce the first method for automatic Image Generation from scene-level freehand sketches. Our model allows for controllable Image Generation by specifying the synthesis goal via freehand sketches. The key contribution is an attribute vector bridged Generative Adversarial Network called EdgeGAN, which supports high visual-quality object-level Image content Generation without using freehand sketches as training data. We have built a large-scale composite dataset called SketchyCOCO to support and evaluate the solution. We validate our approach on the tasks of both object-level and scene-level Image Generation on SketchyCOCO. Through quantitative, qualitative results, human evaluation and ablation studies, we demonstrate the method's capacity to generate realistic complex scene-level Images from various freehand sketches.

Aliaksandr Siarohin - One of the best experts on this subject based on the ideXlab platform.

  • WACV - Attention-based Fusion for Multi-source Human Image Generation
    2020 IEEE Winter Conference on Applications of Computer Vision (WACV), 2020
    Co-Authors: Stéphane Lathuilière, Aliaksandr Siarohin, Enver Sangineto, Nicu Sebe
    Abstract:

    We present a generalization of the person-Image Generation task, in which a human Image is generated conditioned on a target pose and a set X of source appearance Images. In this way, we can exploit multiple, possibly complementary Images of the same person which are usually available at training and at testing time. The solution we propose is mainly based on a local attention mechanism which selects relevant information from different source Image regions, avoiding the necessity to build specific generators for each specific cardinality of X. The empirical evaluation of our method shows the practical interest of addressing the person-Image Generation problem in a multi-source setting.

  • Attention-based Fusion for Multi-source Human Image Generation
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
    Co-Authors: Aliaksandr Siarohin, Stéphane Lathuilière, Enver Sangineto, Nicu Sebe
    Abstract:

    We present a generalization of the person-Image Generation task, in which a human Image is generated conditioned on a target pose and a set X of source appearance Images. In this way, we can exploit multiple, possibly complementary Images of the same person which are usually available at training and at testing time. The solution we propose is mainly based on a local attention mechanism which selects relevant information from different source Image regions, avoiding the necessity to build specific generators for each specific cardinality of X. The empirical evaluation of our method shows the practical interest of addressing the person-Image Generation problem in a multi-source setting.

Stéphane Lathuilière - One of the best experts on this subject based on the ideXlab platform.

  • WACV - Attention-based Fusion for Multi-source Human Image Generation
    2020 IEEE Winter Conference on Applications of Computer Vision (WACV), 2020
    Co-Authors: Stéphane Lathuilière, Aliaksandr Siarohin, Enver Sangineto, Nicu Sebe
    Abstract:

    We present a generalization of the person-Image Generation task, in which a human Image is generated conditioned on a target pose and a set X of source appearance Images. In this way, we can exploit multiple, possibly complementary Images of the same person which are usually available at training and at testing time. The solution we propose is mainly based on a local attention mechanism which selects relevant information from different source Image regions, avoiding the necessity to build specific generators for each specific cardinality of X. The empirical evaluation of our method shows the practical interest of addressing the person-Image Generation problem in a multi-source setting.

  • Attention-based Fusion for Multi-source Human Image Generation
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
    Co-Authors: Aliaksandr Siarohin, Stéphane Lathuilière, Enver Sangineto, Nicu Sebe
    Abstract:

    We present a generalization of the person-Image Generation task, in which a human Image is generated conditioned on a target pose and a set X of source appearance Images. In this way, we can exploit multiple, possibly complementary Images of the same person which are usually available at training and at testing time. The solution we propose is mainly based on a local attention mechanism which selects relevant information from different source Image regions, avoiding the necessity to build specific generators for each specific cardinality of X. The empirical evaluation of our method shows the practical interest of addressing the person-Image Generation problem in a multi-source setting.