Single-image super-resolution via joint statistic models-guided deep auto-encoder network
Sign Up to like & getrecommendations! Published in 2018 at "Neural Computing and Applications"
DOI: 10.1007/s00521-018-3886-2
Abstract: Recent researches on super-resolution (SR) with deep learning networks have achieved amazing results. However, most of the existing studies neglect the internal distinctiveness of an image and the output of most methods tends to be… read more here.
Keywords: image; network; super resolution; model ... See more keywords
Single image super resolution for texture images through neighbor embedding
Sign Up to like & getrecommendations! Published in 2017 at "Multimedia Tools and Applications"
DOI: 10.1007/s11042-017-5367-5
Abstract: This article proposes an improved learning based super resolution scheme using manifold learning for texture images. Pseudo Zernike moment (PZM) has been employed to extract features from the texture images. In order to efficiently retrieve… read more here.
Keywords: super resolution; texture images; image super; texture ... See more keywords
Adaptive dehazing control factor based fast single image dehazing
Sign Up to like & getrecommendations! Published in 2019 at "Multimedia Tools and Applications"
DOI: 10.1007/s11042-019-08120-z
Abstract: The single image dehazing is performed using atmospheric scattering model (ASM). The ASM is based on transmission and atmospheric light. Thus, accurate estimation of transmission is essential for quality single image dehazing. Single image dehazing… read more here.
Keywords: image; dehazing control; image dehazing; control factor ... See more keywords
CSIDNet: Compact single image dehazing network for outdoor scene enhancement
Sign Up to like & getrecommendations! Published in 2020 at "Multimedia Tools and Applications"
DOI: 10.1007/s11042-020-09496-z
Abstract: This paper proposes a novel deep learning-based single image dehazing network named as Compact Single Image Dehazing Network (CSIDNet) for outdoor scene enhancement. CSIDNet directly outputs a haze-free image from the given hazy input. The… read more here.
Keywords: image; image dehazing; csidnet; dehazing network ... See more keywords
Conditional generative adversarial network with densely-connected residual learning for single image super-resolution
Sign Up to like & getrecommendations! Published in 2021 at "Multimedia Tools and Applications"
DOI: 10.1007/s11042-020-09817-2
Abstract: Recently, generative adversarial network (GAN) has been widely employed in single image super-resolution (SISR), achieving favorably good perceptual effects. However, the SR outputs generated by GAN still have some fictitious details, which are quite different… read more here.
Keywords: adversarial network; resolution; generative adversarial; single image ... See more keywords
Visibility restoration of single image captured in dust and haze weather conditions
Sign Up to like & getrecommendations! Published in 2020 at "Multidimensional Systems and Signal Processing"
DOI: 10.1007/s11045-019-00678-z
Abstract: Inclement weather existence of fog, haze, and dust generally degrades the visibility of outdoor images. Bad visibility may cause failure in computer vision applications. Existing dehazing methods cannot work well on dust haze images. Such… read more here.
Keywords: haze images; haze; visibility; single image ... See more keywords
Residual Contextual Hourglass Network for Single-Image Deraining
Sign Up to like & getrecommendations! Published in 2024 at "Neural Processing Letters"
DOI: 10.1007/s11063-024-11541-z
Abstract: Rain streaks could blur and distort images, significantly impacting further image processing. Single-image deraining is a hotspot and has practical application value, while most existing methods still have problems such as residual rain streaks and… read more here.
Keywords: residual contextual; hourglass network; image; contextual hourglass ... See more keywords
Learning Single-Image 3D Reconstruction by Generative Modelling of Shape, Pose and Shading
Sign Up to like & getrecommendations! Published in 2019 at "International Journal of Computer Vision"
DOI: 10.1007/s11263-019-01219-8
Abstract: We present a unified framework tackling two problems: class-specific 3D reconstruction from a single image, and generation of new 3D shape samples. These tasks have received considerable attention recently; however, most existing approaches rely on… read more here.
Keywords: reconstruction; shape; supervised methods; shape pose ... See more keywords
Reblurring-Guided Single Image Defocus Deblurring: A Learning Framework with Misaligned Training Pairs
Sign Up to like & getrecommendations! Published in 2024 at "International Journal of Computer Vision"
DOI: 10.1007/s11263-025-02522-3
Abstract: For single image defocus deblurring, acquiring well-aligned training pairs (or training triplets), i.e., a defocus blurry image, an all-in-focus sharp image (and a defocus blur map), is a challenging task for developing effective deblurring models.… read more here.
Keywords: defocus; image; image defocus; training pairs ... See more keywords
A fast single-image super-resolution via directional edge-guided regularized extreme learning regression
Sign Up to like & getrecommendations! Published in 2017 at "Signal, Image and Video Processing"
DOI: 10.1007/s11760-016-1045-8
Abstract: The goal of super-resolution (SR) is to increase the spatial resolution of a low-resolution (LR) image by a certain factor using either single or multiple LR input images. This paper presents a machine learning-based approach… read more here.
Keywords: resolution; directional edge; image; regularized extreme ... See more keywords
Single-image super-resolution reconstruction using dark channel regularization network
Sign Up to like & getrecommendations! Published in 2021 at "Signal, Image and Video Processing"
DOI: 10.1007/s11760-020-01762-9
Abstract: For single-image super-resolution (SR), deep learning-based approaches have attained superior performance that overshadow all previous approaches. Most recently published deep learning-based single-image SR approaches rely on either deeper or more complex network to achieve further… read more here.
Keywords: resolution; image; network; single image ... See more keywords