Results 31 to 40 of about 596,937 (313)
Image Denoising With Generative Adversarial Networks and its Application to Cell Image Enhancement
IEEE Access, 2020 This paper proposes an image denoising training framework based on Wasserstein Generative Adversarial Networks (WGAN) and applies it to cell image denoising. Cell image denoising is a challenging task which has high requirement on the recovery of feature
Songkui Chen +3 more
doaj +1 more source
Training Image Estimators without Image Ground-Truth
CoRR, 2019 Deep neural networks have been very successful in image estimation applications such as compressive-sensing and image restoration, as a means to estimate images from partial, blurry, or otherwise degraded measurements. These networks are trained on a large number of corresponding pairs of measurements and ground-truth images, and thus implicitly learn ...
Zhihao Xia, Ayan Chakrabarti
openaire +3 more sources
Sensors, 2023 Defocus is an important factor that causes image quality degradation of optoelectronic tracking equipment in the shooting range. In this paper, an improved blind/referenceless image spatial quality evaluator (BRISQUE) algorithm is formulated by using the
Ning Zhang, Cui Lin
doaj +1 more source
Hybrid image representation methods for automatic image annotation: a survey [PDF]
, 2012 In most automatic image annotation systems, images are represented with low level features using either global methods or local methods. In global methods, the entire image is used as a unit.
Oukid, Saliha +7 more
core +1 more source
Grounded Language-Image Pre-training
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022 This paper presents a grounded language-image pre-training (GLIP) model for learning object-level, language-aware, and semantic-rich visual representations. GLIP unifies object detection and phrase grounding for pre-training. The unification brings two benefits: 1) it allows GLIP to learn from both detection and grounding data to improve both tasks and
Liunian Harold Li +11 more
openaire +2 more sources
On Pre-trained Image Features and Synthetic Images for Deep Learning [PDF]
, 2019 Deep Learning methods usually require huge amounts of training data to perform at their full potential, and often require expensive manual labeling. Using synthetic images is therefore very attractive to train object detectors, as the labeling comes for free, and several approaches have been proposed to combine synthetic and real images for training ...
Stefan Hinterstoisser +3 more
openaire +2 more sources
Scientific Reports, 2023 Motion artefacts caused by the patient’s body movements affect magnetic resonance imaging (MRI) accuracy. This study aimed to compare and evaluate the accuracy of motion artefacts correction using a conditional generative adversarial network (CGAN) with ...
Keisuke Usui +7 more
doaj +1 more source
Journal of Electrical Systems and Information Technology, 2017 The crystalline silicon photovoltaic modules are widely used as power supply sources in the tropical areas where the weather conditions change abruptly. Fortunately, many MPPT algorithms are implemented to improve their performance. In the other hand, it
Abraham Dandoussou +4 more
doaj +1 more source
BDIS: Balanced Training Architecture for Dual Image Scaler Using Origin Referenceable Losses
IEEE Access, 2022 Deep neural network (DNN)-based research on image scaling has mostly focused on super-resolution (SR) rather than image downscaling. Specifically, most existing DNN-based methods for image downscaling are used as auxiliary modules to improve the quality ...
Eun Su Kang +4 more
doaj +1 more source
Image Enhancement Network Trained by Using HDR images
CoRR, 2019 Under ...
Yuma Kinoshita, Hitoshi Kiya
openaire +2 more sources