On the use of deep learning for computational imaging

G Barbastathis, A Ozcan, G Situ - Optica, 2019 - opg.optica.org
Since their inception in the 1930–1960s, the research disciplines of computational imaging
and machine learning have followed parallel tracks and, during the last two decades …

Dictionaries for sparse representation modeling

R Rubinstein, AM Bruckstein, M Elad - Proceedings of the IEEE, 2010 - ieeexplore.ieee.org
Sparse and redundant representation modeling of data assumes an ability to describe
signals as linear combinations of a few atoms from a pre-specified dictionary. As such, the …

[PDF][PDF] 图像的多尺度几何分析: 回顾和展望

焦**成, 谭山 - 电子学报, 2003 - ejournal.org.cn
图像的多尺度几何分析:回顾和展望 Page 1 图像的多尺度几何分析:回顾和展望 焦**成,谭山 (西安
电子科技大学雷达信号处理国家重点实验室和智能信息处理研究所,陕西西安710071) 摘要: 多尺度 …

Making convolutional networks shift-invariant again

R Zhang - International conference on machine learning, 2019 - proceedings.mlr.press
Modern convolutional networks are not shift-invariant, as small input shifts or translations
can cause drastic changes in the output. Commonly used downsampling methods, such as …

Why do deep convolutional networks generalize so poorly to small image transformations?

A Azulay, Y Weiss - Journal of Machine Learning Research, 2019 - jmlr.org
Abstract Convolutional Neural Networks (CNNs) are commonly assumed to be invariant to
small image transformations: either because of the convolutional architecture or because …

End-to-end optimized image compression

J Ballé, V Laparra, EP Simoncelli - arxiv preprint arxiv:1611.01704, 2016 - arxiv.org
We describe an image compression method, consisting of a nonlinear analysis
transformation, a uniform quantizer, and a nonlinear synthesis transformation. The …

Deep generative image models using a laplacian pyramid of adversarial networks

EL Denton, S Chintala… - Advances in neural …, 2015 - proceedings.neurips.cc
In this paper we introduce a generative model capable of producing high quality samples of
natural images. Our approach uses a cascade of convolutional networks (convnets) within a …

Learning a no-reference quality metric for single-image super-resolution

C Ma, CY Yang, X Yang, MH Yang - Computer Vision and Image …, 2017 - Elsevier
Numerous single-image super-resolution algorithms have been proposed in the literature,
but few studies address the problem of performance evaluation based on visual perception …

A survey of sparse representation: algorithms and applications

Z Zhang, Y Xu, J Yang, X Li, D Zhang - IEEE access, 2015 - ieeexplore.ieee.org
Sparse representation has attracted much attention from researchers in fields of signal
processing, image processing, computer vision, and pattern recognition. Sparse …

dipIQ: Blind image quality assessment by learning-to-rank discriminable image pairs

K Ma, W Liu, T Liu, Z Wang… - IEEE Transactions on …, 2017 - ieeexplore.ieee.org
Objective assessment of image quality is fundamentally important in many image processing
tasks. In this paper, we focus on learning blind image quality assessment (BIQA) models …