The Experts below are selected from a list of 31746 Experts worldwide ranked by ideXlab platform

Tao Yue - One of the best experts on this subject based on the ideXlab platform.

  • enhancing low light videos by exploring high sensitivity Camera Noise
    International Conference on Computer Vision, 2019
    Co-Authors: Wei Wang, Xin Chen, Cheng Yang, Tao Yue
    Abstract:

    Enhancing low light videos, which consists of denoising and brightness adjustment, is an intriguing but knotty problem. Under low light condition, due to high sensitivity Camera setting, commonly negligible Noises become obvious and severely deteriorate the captured videos. To recover high quality videos, a mass of image/video denoising/enhancing algorithms are proposed, most of which follow a set of simple assumptions about the statistic characters of Camera Noise, e.g., independent and identically distributed(i.i.d.), white, additive, Gaussian, Poisson or mixture Noises. However, the practical Noise under high sensitivity setting in real captured videos is complex and inaccurate to model with these assumptions. In this paper, we explore the physical origins of the practical high sensitivity Noise in digital Cameras, model them mathematically, and propose to enhance the low light videos based on the Noise model by using an LSTM-based neural network. Specifically, we generate the training data with the proposed Noise model and train the network with the dark noisy video as input and clear-bright video as output. Extensive comparisons on both synthetic and real captured low light videos with the state-of-the-art methods are conducted to demonstrate the effectiveness of the proposed method.

  • ICCV - Enhancing Low Light Videos by Exploring High Sensitivity Camera Noise
    2019 IEEE CVF International Conference on Computer Vision (ICCV), 2019
    Co-Authors: Wei Wang, Cheng Yang, Chen Xin, Tao Yue
    Abstract:

    Enhancing low light videos, which consists of denoising and brightness adjustment, is an intriguing but knotty problem. Under low light condition, due to high sensitivity Camera setting, commonly negligible Noises become obvious and severely deteriorate the captured videos. To recover high quality videos, a mass of image/video denoising/enhancing algorithms are proposed, most of which follow a set of simple assumptions about the statistic characters of Camera Noise, e.g., independent and identically distributed(i.i.d.), white, additive, Gaussian, Poisson or mixture Noises. However, the practical Noise under high sensitivity setting in real captured videos is complex and inaccurate to model with these assumptions. In this paper, we explore the physical origins of the practical high sensitivity Noise in digital Cameras, model them mathematically, and propose to enhance the low light videos based on the Noise model by using an LSTM-based neural network. Specifically, we generate the training data with the proposed Noise model and train the network with the dark noisy video as input and clear-bright video as output. Extensive comparisons on both synthetic and real captured low light videos with the state-of-the-art methods are conducted to demonstrate the effectiveness of the proposed method.

Sebastian Thrun - One of the best experts on this subject based on the ideXlab platform.

  • design and calibration of a multi view tof sensor fusion system
    Computer Vision and Pattern Recognition, 2008
    Co-Authors: Young Min Kim, Derek Y Chan, Christian Theobalt, Sebastian Thrun
    Abstract:

    This paper describes the design and calibration of a system that enables simultaneous recording of dynamic scenes with multiple high-resolution video and low-resolution Swissranger time-of-flight (TOF) depth Cameras. The system shall serve as a testbed for the development of new algorithms for high-quality multi-view dynamic scene reconstruction and 3D video. The paper also provides a detailed analysis of random and systematic depth Camera Noise which is important for reliable fusion of video and depth data. Finally, the paper describes how to compensate systematic depth errors and calibrate all dynamic depth and video data into a common frame.

  • CVPR Workshops - Design and calibration of a multi-view TOF sensor fusion system
    2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2008
    Co-Authors: Young Min Kim, Derek Y Chan, Christian Theobalt, Sebastian Thrun
    Abstract:

    This paper describes the design and calibration of a system that enables simultaneous recording of dynamic scenes with multiple high-resolution video and low-resolution Swissranger time-of-flight (TOF) depth Cameras. The system shall serve as a testbed for the development of new algorithms for high-quality multi-view dynamic scene reconstruction and 3D video. The paper also provides a detailed analysis of random and systematic depth Camera Noise which is important for reliable fusion of video and depth data. Finally, the paper describes how to compensate systematic depth errors and calibrate all dynamic depth and video data into a common frame.

R. Parolari - One of the best experts on this subject based on the ideXlab platform.

  • Statistical characteristics of granular Camera Noise
    IEEE Transactions on Circuits and Systems for Video Technology, 1994
    Co-Authors: Guido M. Cortelazzo, Gian Antonio Mian, R. Parolari
    Abstract:

    Granular Camera Noise is per se objectionable in high-quality TV and it is a source of bothersome visual artifacts with digitally coded video sequences. The first and second order statistical characteristics of this Noise are investigated in this work. The results quantify intuitively expected notions, such as the relative unimportance of chrominance Noise with respect to the luminance Noise and the spatially colored nature of the Noise. Noise reduction techniques can use, as general guidance rules, the indications of the presented analysis. >

I.m. Woodhead - One of the best experts on this subject based on the ideXlab platform.

  • A Technique for Evaluation of CCD Video-Camera Noise
    IEEE Transactions on Circuits and Systems for Video Technology, 2008
    Co-Authors: K. Irie, A.e. Mckinnon, K. Unsworth, I.m. Woodhead
    Abstract:

    This paper presents a technique to identify and measure the prominent sources of sensor Noise in commercially available charge-coupled device (CCD) video Cameras by analysis of the output images. Noise fundamentally limits the distinguishable content in an image and can significantly reduce the robustness of an image processing application. Although sources of image sensor Noise are well documented, there has been little work on the development of techniques to identify and quantify the types of Noise present in CCD video-Camera images. A comprehensive Noise model for CCD Cameras was used to evaluate the technique on a commercially available CCD video Camera.

Manuel M. Oliveira - One of the best experts on this subject based on the ideXlab platform.

  • Synthesizing Camera Noise Using Generative Adversarial Networks
    IEEE transactions on visualization and computer graphics, 2021
    Co-Authors: Bernardo Henz, Eduardo Simoes Lopes Gastal, Manuel M. Oliveira
    Abstract:

    We present a technique for synthesizing realistic Noise for digital photographs. It can adjust the Noise level of an input photograph, either increasing or decreasing it, to match a target ISO level. Our solution learns the mappings among different ISO levels from unpaired data using generative adversarial networks. We demonstrate its effectiveness both quantitatively, using Kullback-Leibler divergence and Kolmogorov-Smirnov test, and qualitatively through a large number of examples. We also demonstrate its practical applicability by using its results to significantly improve the performance of a state-of-the-art trainable denoising method. Our technique should benefit several computer-vision applications that seek robustness to noisy scenarios.