The quality assessment (QA) of restored low-light images is an important tool for benchmarking and improving low-light restoration (LLR) algorithms. While several LLR algorithms exist, the subjective ...perception of the restored images has been much less studied. Challenges in capturing aligned low-light and well-lit image pairs and collecting a large number of human opinion scores of quality for training, warrant the design of unsupervised (or opinion unaware) no-reference (NR) QA methods. This work studies the subjective perception of low-light restored images and their unsupervised NR QA. Our contributions are two-fold. We first create a dataset of restored low-light images using various LLR methods, conduct a subjective QA study, and benchmark the performance of existing QA methods. We then present a self-supervised contrastive learning technique to extract distortion-aware features from the restored low-light images. We show that these features can be effectively used to build an opinion unaware image quality analyzer. Detailed experiments reveal that our unsupervised NR QA model achieves state-of-the-art performance among all such quality measures for low-light restored images.
We study the problem of joint low light image contrast enhancement and denoising using a statistical approach. The low light natural image in the band pass domain is modeled by statistically relating ...a Gaussian scale mixture model for the pristine image, to the low light image, through a detail loss coefficient and Gaussian noise. The detail loss coefficient is statistically described using a posterior distribution with respect to its estimate based on a prior contrast enhancement algorithm. We then design our low light enhancement and denoising (LLEAD) method by computing the minimum mean squared error estimate of the pristine image band pass coefficients. We create the Indian Institute of Science low light image dataset of well-lit and low light image pairs to learn the model parameters and evaluate our enhancement method. We show through extensive experiments on multiple datasets that our method helps better enhance the contrast while simultaneously controlling the noise when compared to other state of the art joint contrast enhancement and denoising methods.
Abstract
In today’s world, economic climate changes more quickly, and countries realise that globalisation has made the world small and more competitive. Also, customers seek products and services ...that can respond to their specific needs, and firms make effort to create competitive advantages to keep their profit and market share. All of the above trends lead firms and countries to focus on efficient logistics system. In this context, almost all developed economies and a few emerging economies estimate national logistics cost on a regular basis to understand the efficiency of their logistics system. This article makes an attempt to survey the literature on logistics cost estimation with special emphasis from the perspective of a developing country like India where estimation is a challenge due to limitation of data.
JEL Codes: D57, E23, P44
Convolutional neural networks have been successful in restoring images captured under poor illumination conditions. Nevertheless, such approaches require a large number of paired low-light and ground ...truth images for training. Thus, we study the problem of semi-supervised learning for low-light image restoration when limited low-light images have ground truth labels. Our main contributions in this work are twofold. We first deploy an ensemble of low-light restoration networks to restore the unlabeled images and generate a set of potential pseudo-labels. We model the contrast distortions in the labeled set to generate different sets of training data and create the ensemble of networks. We then design a contrastive self-supervised learning based image quality measure to obtain the pseudo-label among the images restored by the ensemble. We show that training the restoration network with the pseudo-labels allows us to achieve excellent restoration performance even with very few labeled pairs. We conduct extensive experiments on three popular low-light image restoration datasets to show the superior performance of our semi-supervised low-light image restoration compared to other approaches. Project page is available at https://github.com/sameerIISc/SSL-LLR.
This paper based on the United Nations Industrial Development Organization (UNIDO) panel data set makes an attempt to estimate total factor productivity growth (TFPG) across countries. Productivity ...convergence over time is evident when countries are divided across regions which could be attributed to a greater degree of association of countries in a given region pursuing joint efforts for infrastructural development, ICT coverage and advancement, trade negotiations, technology acquisition and innovation, and inflow of FDI. In terms of efficiency estimates for select years, most of the countries are seen to be operating much below the frontier. This is indicative of the fact that countries are keen to pursue resource-driven growth in an attempt to maximize it. Based on the inter-temporal data, we observed that a number of countries registered either a negative or a positive but low correlation between labour productivity growth and TFPG. Evidently, countries are engaged in greater mechanization which may be raising labour productivity without ushering in much success in terms of TFPG. From panel data regression, the impact of technology perceived in terms of TFPG, on employment, is seen to be negligible though it is important to note that none of the groups, income or region-wise, recorded a statistically significant negative effect except the least developed countries (LDCs), while the significant cases (howsoever scanty) reveal a positive association. Appropriate incentives may motivate firms to experience technological progress and employment growth both.
Natural ion‐transporters in cellular membranes play a critical role in maintaining cell homeostasis. Synthetic ion‐transporters are attractive model systems for understanding and addressing ...dysfunction of natural transporters. Herein, a simple amide derived from azobenzene and m‐aminobenzoic acid achieves photoregulated ion transport across lipid membranes. The amide forms pores or channels that selectively co‐transport H+/X– across the lipid membrane. Photoisomerization from the trans to cis form results in a 2‐fold increase in ion‐transport rates due to the higher proton affinity of the cis isomer.
We consider the problem of low light image restoration through joint contrast enhancement and denoising. Deep convolutional neural networks (CNNs) based on residual learning have been successful in ...achieving state of the art performance in image denoising. However, their application to joint contrast enhancement and denoising poses challenges owing to the nature of the distortion process involving both loss of details and noise. Thus, we propose a multiscale learning approach by learning the subbands obtained in a Laplacian pyramid decomposition through a subband CNN (SCNN). The enhanced subbands at multiple scales are then combined to obtain the final restored image using a recomposition CNN (ReCNN). We refer to the overall network involving SCNN and ReCNN as low light restoration network (LLRNet). We show through extensive experiments based on the `See in the Dark' Dataset that our approach produces better quality restored images when compared to other contrast enhancement techniques and CNN based approaches.
We study the problem of low light image restoration through contrast enhancement and denoising. We approach this problem by learning a model that relates a noisy low light and well lit image pair. ...The low light image is modeled to suffer from contrast distortion and additive noise. In particular, we model the loss of contrast through a global parametric function, which enables the estimation of the underlying noise. We then use a pair of convolutional neural network (CNN) models to learn the noise and the parameters of a function to achieve contrast enhancement. This contrast enhancement function is modeled as a linear combination of multiple gamma enhancers. We show through extensive evaluations that our Low Light Image Model for Enhancement Network (LLIMENet) achieves superior restoration performance when compared to other methods on several publicly available datasets.
PDF
