We present a comprehensive study and evaluation of existing single-image dehazing algorithms, using a new large-scale benchmark consisting of both synthetic and real-world hazy images, called REalistic Single-Image DEhazing (RESIDE). RESIDE highlights diverse data sources and image contents, and is divided into five subsets, each serving different training or evaluation purposes. We further provide a rich variety of criteria for dehazing algorithm evaluation, ranging from full-reference metrics to no-reference metrics and to subjective evaluation, and the novel task-driven evaluation. Experiments on RESIDE shed light on the comparisons and limitations of the state-of-the-art dehazing algorithms, and suggest promising future directions.

Benchmarking Single-Image Dehazing and Beyond

Deep learning-based methods have achieved remarkable success in image restoration and enhancement, but are they still competitive when there is a lack of paired training data? As one such example, this paper explores the low-light image enhancement problem, where in practice it is extremely challenging to simultaneously take a low-light and a normal-light photo of the same visual scene. We propose a highly effective unsupervised generative adversarial network, dubbed EnlightenGAN , that can be trained without low/normal-light image pairs, yet proves to generalize very well on various real-world test images. Instead of supervising the learning using ground truth data, we propose to regularize the unpaired training using the information extracted from the input itself, and benchmark a series of innovations for the low-light image enhancement problem, including a global-local discriminator structure, a self-regularized perceptual loss fusion, and the attention mechanism. Through extensive experiments, our proposed approach outperforms recent methods under a variety of metrics in terms of visual quality and subjective user study. Thanks to the great flexibility brought by unpaired training, EnlightenGAN is demonstrated to be easily adaptable to enhancing real-world images from various domains. Our codes and pre-trained models are available at: https://github.com/VITA-Group/EnlightenGAN .

EnlightenGAN: Deep Light Enhancement Without Paired Supervision

Deep learning-based methods have achieved remarkable success in image restoration and enhancement, but are they still competitive when there is a lack of paired training data? As one such example, this paper explores the low-light image enhancement problem, where in practice it is extremely challenging to simultaneously take a low-light and a normal-light photo of the same visual scene. We propose a highly effective unsupervised generative adversarial network, dubbed EnlightenGAN, that can be trained without low/normal-light image pairs, yet proves to generalize very well on various real-world test images. Instead of supervising the learning using ground truth data, we propose to regularize the unpaired training using the information extracted from the input itself, and benchmark a series of innovations for the low-light image enhancement problem, including a global-local discriminator structure, a self-regularized perceptual loss fusion, and attention mechanism. Through extensive experiments, our proposed approach outperforms recent methods under a variety of metrics in terms of visual quality and subjective user study. Thanks to the great flexibility brought by unpaired training, EnlightenGAN is demonstrated to be easily adaptable to enhancing real-world images from various domains. The code is available at \url{this https URL}

pdf/enlightengan-deep-light-enhancement-without-paired-27i8jcir63.pdf

EnlightenGAN: Deep Light Enhancement without Paired Supervision

Single image dehazing has been a challenging problem which aims to recover clear images from hazy ones. The performance of existing image dehazing methods is limited by hand-designed features and priors. In this paper, we propose a multi-scale deep neural network for single image dehazing by learning the mapping between hazy images and their transmission maps. The proposed algorithm consists of a coarse-scale net which predicts a holistic transmission map based on the entire image, and a fine-scale net which refines dehazed results locally. To train the multi-scale deep network, we synthesize a dataset comprised of hazy images and corresponding transmission maps based on the NYU Depth dataset. In addition, we propose a holistic edge guided network to refine edges of the estimated transmission map. Extensive experiments demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods on both synthetic and real-world images in terms of quality and speed.

Single Image Dehazing via Multi-scale Convolutional Neural Networks with Holistic Edges

We present a comprehensive study and evaluation of existing single image deraining algorithms, using a new large-scale benchmark consisting of both synthetic and real-world rainy images.This dataset highlights diverse data sources and image contents, and is divided into three subsets (rain streak, rain drop, rain and mist), each serving different training or evaluation purposes. We further provide a rich variety of criteria for dehazing algorithm evaluation, ranging from full-reference metrics, to no-reference metrics, to subjective evaluation and the novel task-driven evaluation. Experiments on the dataset shed light on the comparisons and limitations of state-of-the-art deraining algorithms, and suggest promising future directions.

/pdf/single-image-deraining-a-comprehensive-benchmark-analysis-3763qb7xnj.pdf

Single Image Deraining: A Comprehensive Benchmark Analysis

Here we explore two related but important tasks based on the recently released REalistic Single Image DEhazing (RESIDE) benchmark dataset: (i) single image dehazing as a low-level image restoration problem; and (ii) high-level visual understanding (e.g., object detection) of hazy images. For the first task, we investigated a variety of loss functions and show that perception-driven loss significantly improves dehazing performance. In the second task, we provide multiple solutions including using advanced modules in the dehazing-detection cascade and domain-adaptive object detectors. In both tasks, our proposed solutions significantly improve performance. GitHub repository URL is: this https URL

Improved Techniques for Learning to Dehaze and Beyond: A Collective Study

Co-training is a major multi-view learning paradigm that alternately trains two classifiers on two distinct views and maximizes the mutual agreement on the two-view unlabeled data. Traditional co-training algorithms usually train a learner on each view separately and then force the learners to be consistent across views. Although many co-trainings have been developed, it is quite possible that a learner will receive erroneous labels for unlabeled data when the other learner has only mediocre accuracy. This usually happens in the first rounds of co-training, when there are only a few labeled examples. As a result, co-training algorithms often have unstable performance. In this paper, Hessian-regularized co-training is proposed to overcome these limitations. Specifically, each Hessian is obtained from a particular view of examples; Hessian regularization is then integrated into the learner training process of each view by penalizing the regression function along the potential manifold. Hessian can properly exploit the local structure of the underlying data manifold. Hessian regularization significantly boosts the generalizability of a classifier, especially when there are a small number of labeled examples and a large number of unlabeled examples. To evaluate the proposed method, extensive experiments were conducted on the unstructured social activity attribute (USAA) dataset for social activity recognition. Our results demonstrate that the proposed method outperforms baseline methods, including the traditional co-training and LapCo algorithms.

/pdf/hessian-regularized-co-training-for-social-activity-3l4dxjblmw.pdf

Hessian-regularized co-training for social activity recognition.

A general framework for co-training and its applications

Spectral clustering employs spectral-graph structure of a similarity matrix to partition data into disjoint meaningful groups, because of its well-defined mathematical framework, good performance and simplicity, spectral clustering has gained considerable attentions in the recent past. Despite these virtues, it suffers from several drawbacks, such as it is unable to determine a reasonable cluster number, sensitive to initial condition and not robust to outliers. In this paper, we present a new approach named density peak spectral clustering (DPSC) which combines spectral clustering with density peak clustering algorithm (DPCA) into a unified framework to solve these problems. Since multi-view data is common in clustering problem, to further bootstrap the clustering performance by using complementary information from different view, then we propose co-trained density peak spectral clustering (Co-DPSC), which is an extension of DPSC to multi-views based on the co-training idea. Experimental comparisons with a number of baselines on a toy and three real-world datasets show the effectiveness of our proposed DPSC and Co-DPSC algorithm.

Co-spectral clustering based density peak

Co-training is one promising paradigm of semi-supervised learning and has drawn considerable attentions and interests in recent years. It usually works in an iterative manner on two disjoint view features, in which two classifiers are trained on the different views and teach each other by adding the predictions of unlabeled data to the training set of the other view. However, the classifier performs not well with small number of labeled examples especially in the first rounds of interation. In this paper, we present Laplacian regularized co-training(LapCo) to address the above problem in standard co-training. During the training process, LapCo employs Laplacian regularization into the classifier to significantly boost the classification performance. The experiments on three popular UCI repository datasets are conducted and show that the proposed LapCo outperforms the traditional co-training method.

Laplacian regularized co-training

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Yang Li

Author Tools

Chat about Author