The Experts below are selected from a list of 12963 Experts worldwide ranked by ideXlab platform

Roberto Passerone - One of the best experts on this subject based on the ideXlab platform.

  • 3DV — An embedded, dense stereovision-based depth mapping system
    2014 IEEE Intelligent Vehicles Symposium Proceedings, 2014
    Co-Authors: Gabriele Camellini, Mirko Felisa, Paolo Medici, Paolo Zani, Francesco Gregoretti, Claudio Passerone, Roberto Passerone
    Abstract:

    This paper describes the architecture and hardware implementation of an embedded, low-cost and low-power dense stereo reconstruction system, running at 30 fps at VGA resolution. The processing pipeline includes an Initial Image rectification stage, a cost generation unit based on the non-parametric census transform, a state-of-the-art Semi-Global cost optimization stage, and a final minimization and noise suppression step. The hardware implementation is based on a Xilinx ZynqTM System-on-Chip, which besides the FPGA provides a physical dual-core ARM CPU, which is exploited for control and to deliver output over the integrated Gigabit Ethernet connection.

  • 3dv an embedded dense stereovision based depth mapping system
    Intelligent Vehicles Symposium, 2014
    Co-Authors: Gabriele Camellini, Mirko Felisa, Paolo Medici, Paolo Zani, Francesco Gregoretti, Claudio Passerone, Roberto Passerone
    Abstract:

    This paper describes the architecture and hardware implementation of an embedded, low-cost and low-power dense stereo reconstruction system, running at 30 fps at VGA resolution. The processing pipeline includes an Initial Image rectification stage, a cost generation unit based on the non-parametric census transform, a state-of-the-art Semi-Global cost optimization stage, and a final minimization and noise suppression step. The hardware implementation is based on a Xilinx ZynqTM System-on-Chip, which besides the FPGA provides a physical dual-core ARM CPU, which is exploited for control and to deliver output over the integrated Gigabit Ethernet connection.

Gabriele Camellini - One of the best experts on this subject based on the ideXlab platform.

  • 3DV — An embedded, dense stereovision-based depth mapping system
    2014 IEEE Intelligent Vehicles Symposium Proceedings, 2014
    Co-Authors: Gabriele Camellini, Mirko Felisa, Paolo Medici, Paolo Zani, Francesco Gregoretti, Claudio Passerone, Roberto Passerone
    Abstract:

    This paper describes the architecture and hardware implementation of an embedded, low-cost and low-power dense stereo reconstruction system, running at 30 fps at VGA resolution. The processing pipeline includes an Initial Image rectification stage, a cost generation unit based on the non-parametric census transform, a state-of-the-art Semi-Global cost optimization stage, and a final minimization and noise suppression step. The hardware implementation is based on a Xilinx ZynqTM System-on-Chip, which besides the FPGA provides a physical dual-core ARM CPU, which is exploited for control and to deliver output over the integrated Gigabit Ethernet connection.

  • 3dv an embedded dense stereovision based depth mapping system
    Intelligent Vehicles Symposium, 2014
    Co-Authors: Gabriele Camellini, Mirko Felisa, Paolo Medici, Paolo Zani, Francesco Gregoretti, Claudio Passerone, Roberto Passerone
    Abstract:

    This paper describes the architecture and hardware implementation of an embedded, low-cost and low-power dense stereo reconstruction system, running at 30 fps at VGA resolution. The processing pipeline includes an Initial Image rectification stage, a cost generation unit based on the non-parametric census transform, a state-of-the-art Semi-Global cost optimization stage, and a final minimization and noise suppression step. The hardware implementation is based on a Xilinx ZynqTM System-on-Chip, which besides the FPGA provides a physical dual-core ARM CPU, which is exploited for control and to deliver output over the integrated Gigabit Ethernet connection.

Stefanos Kollias - One of the best experts on this subject based on the ideXlab platform.

  • Confronting the Synchronization Problem of Semantic Region Under Geometric Attacks
    2006 IEEE International Conference on Multimedia and Expo, 2006
    Co-Authors: Paraskevi Tzouveli, Klimis Ntalianis, Stefanos Kollias
    Abstract:

    In this paper, an affine invariant watermarking scheme, robust to geometric attacks, is proposed and applied to face regions. Initially, face regions are unsupervisedly extracted from an Initial Image and a normalization procedure, invariant to geometric attacks is applied on each of these regions using a set of specific moment criteria. A spread spectrum-based DS-CDMA watermarking scheme is then used in order to provide a multi bits watermark. The multi bits watermark embedding and detection procedures are then applicable to each normalized face region. Finally, performance of the proposed face regions watermarking scheme is tested under various distortions, providing efficient and robust watermark retrieval

P. Chainais - One of the best experts on this subject based on the ideXlab platform.

  • Virtual Super Resolution of Scale Invariant Textured Images Using Multifractal Stochastic Processes
    Journal of Mathematical Imaging and Vision, 2011
    Co-Authors: P. Chainais, Véronique Delouille, Jean-françois Hochedez
    Abstract:

    We present a new method of magnification for textured Images featuring scale invariance properties. This work is originally motivated by an application to astronomical Images. One goal is to propose a method to quantitatively predict statistical and visual properties of Images taken by a forthcoming higher resolution telescope from older Images at lower resolution. This is done by performing a virtual super resolution using a family of scale invariant stochastic processes, namely compound Poisson cascades, and fractional integration. The procedure preserves the visual aspect as well as the statistical properties of the Initial Image. An augmentation of information is performed by locally adding random small scale details below the Initial pixel size. This extrapolation procedure yields a potentially infinite number of magnified versions of an Image. It allows for large magnification factors (virtually infinite) and is physically conservative: zooming out to the Initial resolution yields the Initial Image back. The (virtually) super resolved Images can be used to predict the quality of future observations as well as to develop and test compression or denoising techniques.

  • Virtual resolution enhancement of scale invariant textured Images using stochastic processes
    2009 16th IEEE International Conference on Image Processing (ICIP), 2009
    Co-Authors: E. Koenig, P. Chainais
    Abstract:

    We present a new method of magnification for textured Images featuring scale invariance properties. The procedure preserves the visual aspect as well as the statistical properties of the Initial Image. An augmentation of information is performed by locally adding small scale details below the Initial pixel size. This is made possible thanks to a family of scale invariant stochastic processes, namely compound Poisson cascades. This extrapolating procedure yields a potentially infinite number of magnified versions of an Image. It allows for large magnification factors (virtually infinite) and is physically conservative: zooming out to the Initial resolution yields the Initial Image back. This work is motivated by an application to Images of the quiet Sun to quantitatively predict statistical and visual properties of Images taken by a forthcoming high resolution telescope.

Yi Yang - One of the best experts on this subject based on the ideXlab platform.

  • DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-To-Image Synthesis
    2019 IEEE CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019
    Co-Authors: Wei Chen, Yi Yang
    Abstract:

    In this paper, we focus on generating realistic Images from text descriptions. Current methods first generate an Initial Image with rough shape and color, and then refine the Initial Image to a high-resolution one. Most existing text-to-Image synthesis methods have two main problems. (1) These methods depend heavily on the quality of the Initial Images. If the Initial Image is not well Initialized, the following processes can hardly refine the Image to a satisfactory quality. (2) Each word contributes a different level of importance when depicting different Image contents, however, unchanged text representation is used in existing Image refinement processes. In this paper, we propose the Dynamic Memory Generative Adversarial Network (DM-GAN) to generate high-quality Images. The proposed method introduces a dynamic memory module to refine fuzzy Image contents, when the Initial Images are not well generated. A memory writing gate is designed to select the important text information based on the Initial Image content, which enables our method to accurately generate Images from the text description. We also utilize a response gate to adaptively fuse the information read from the memories and the Image features. We evaluate the DM-GAN model on the Caltech-UCSD Birds 200 dataset and the Microsoft Common Objects in Context dataset. Experimental results demonstrate that our DM-GAN model performs favorably against the state-of-the-art approaches.

  • CVPR - DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-To-Image Synthesis
    2019 IEEE CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019
    Co-Authors: Wei Chen, Yi Yang
    Abstract:

    In this paper, we focus on generating realistic Images from text descriptions. Current methods first generate an Initial Image with rough shape and color, and then refine the Initial Image to a high-resolution one. Most existing text-to-Image synthesis methods have two main problems. (1) These methods depend heavily on the quality of the Initial Images. If the Initial Image is not well Initialized, the following processes can hardly refine the Image to a satisfactory quality. (2) Each word contributes a different level of importance when depicting different Image contents, however, unchanged text representation is used in existing Image refinement processes. In this paper, we propose the Dynamic Memory Generative Adversarial Network (DM-GAN) to generate high-quality Images. The proposed method introduces a dynamic memory module to refine fuzzy Image contents, when the Initial Images are not well generated. A memory writing gate is designed to select the important text information based on the Initial Image content, which enables our method to accurately generate Images from the text description. We also utilize a response gate to adaptively fuse the information read from the memories and the Image features. We evaluate the DM-GAN model on the Caltech-UCSD Birds 200 dataset and the Microsoft Common Objects in Context dataset. Experimental results demonstrate that our DM-GAN model performs favorably against the state-of-the-art approaches.