Features obtained from object recognition CNNs have been widely used for measuring perceptual similarities between images. Such differentiable metrics can be used as perceptual learning losses to train image enhancement models. However, the choice of the distance function between input and target features may have a consequential impact on the performance of the trained model. While using the norm of the difference between extracted features leads to limited hallucination of details, measuring the distance between distributions of features may generate more textures; yet also more unrealistic details and artifacts. In this paper, we demonstrate that aggregating 1D-Wasserstein distances between CNN activations is more reliable than the existing approaches, and it can significantly improve the perceptual performance of enhancement models. More explicitly, we show that in imaging applications such as denoising, super-resolution, demosaicing, deblurring and JPEG artifact removal, the proposed learning loss outperforms the current state-of-the-art on reference-based perceptual losses. This means that the proposed learning loss can be plugged into different imaging frameworks and produce perceptually realistic results.
Indian Institute of Information Technology and Management- Kerala（喀拉拉邦信息技术与管理学院）
Anisotropic Diffusion is widely used for noise reduction with simultaneous preservation of vascular structures in maximum intensity projected (MIP) angiograms. However, extension to minimum intensity projected (mIP) venograms in Susceptibility Weighted Imaging (SWI) poses difficulties due to spatially varying baseline. Here, we introduce a modified version of the directional anisotropic diffusion which allows us to simultaneously reduce the noise and enhance vascular structures reconstructed using both M/mIP angiograms. This method is based on spatial adaptation of the diffusion function, sepa…
Tel-Aviv University（特拉维夫大学）；Ulsan National Institute of Science and Technology（蔚山国立科学技术院）；Weizmann Institute of Science（魏茨曼科学研究所）
Ill-posed inverse problems appear in many image processing applications, such as deblurring and super-resolution. In recent years, solutions that are based on deep Convolutional Neural Networks (CNNs) have shown great promise. Yet, most of these techniques, which train CNNs using external data, are restricted to the observation models that have been used in the training phase. A recent alternative that does not have this drawback relies on learning the target image using internal learning. One such prominent example is the Deep Image Prior (DIP) technique that trains a network directly on the …
Existing unpaired low-light image enhancement approaches prefer to employ the two-way GAN framework, in which two CNN generators are deployed for enhancement and degradation separately. However, such data-driven models ignore the inherent characteristics of transformation between the low and normal light images, leading to unstable training and artifacts. Here, we propose to leverage the invertible network to enhance low-light image in forward process and degrade the normal-light one inversely with unpaired learning. The generated and real images are then fed into discriminators for adversaria…
Learning a typical image enhancement pipeline involves minimization of a loss function between enhanced and reference images. While L1 and L2 losses are perhaps the most widely used functions for this purpose, they do not necessarily lead to perceptually compelling results. In this paper, we show that adding a learned no-reference image quality metric to the loss can significantly improve enhancement operators. This metric is implemented using a CNN (convolutional neural network) trained on a large-scale dataset labelled with aesthetic preferences of human raters. This loss allows us to conven…
Nanjing University of Information Science and Technology（南京信息工程大学）
Underwater image enhancement algorithms have attracted much attention in underwater vision task. However, these algorithms are mainly evaluated on different data sets and different metrics. In this paper, we set up an effective and pubic underwater test dataset named U45 including the color casts, low contrast and haze-like effects of underwater degradation and propose a fusion adversarial network for enhancing underwater images. Meanwhile, the well-designed the adversarial loss including Lgt loss and Lfe loss is presented to focus on image features of ground truth, and image features of the i…
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
Restoring images from low-light data is a challenging problem. Most existing deep-network based algorithms are designed to be trained with pairwise images. Due to the lack of real-world datasets, they usually perform poorly when generalized in practice in terms of loss of image edge and color information. In this paper, we propose an unsupervised generation network with attention-guidance to handle the low-light image enhancement task. Specifically, our network contains two parts: an edge auxiliary module that restores sharper edges and an attention guidance module that recovers more realistic…
Anyvision（安视维）；Queen’s University Belfast（贝尔法斯特女王大学）
Despite the breakthroughs in quality of image enhancement, an end-to-end solution for simultaneous recovery of the finer texture details and sharpness for degraded images with low resolution is still unsolved. Some existing approaches focus on minimizing the pixel-wise reconstruction error which results in a high peak signal-to-noise ratio. The enhanced images fail to provide high-frequency details and are perceptually unsatisfying, i.e., they fail to match the quality expected in a photo-realistic image. In this paper, we present Image Enhancement Generative Adversarial Network (IEGAN), a ver…
A Non-Uniform Low-Light Image Enhancement Method with Multi-Scale Attention Transformer and Luminance Consistency Loss
Beijing University of Posts and Telecommunications（北京邮电大学）；China Electric Power Research Institute Company Limited（中国电力科学研究院有限公司）；Tianjin University（天津大学）；State Grid Shanxi Marketing Service Center（国网山西省电力公司营销服务中心）
Adversarial examples are intentionally perturbed images that mislead classifiers. These images can, however, be easily detected using denoising algorithms, when high-frequency spatial perturbations are used, or can be noticed by humans, when perturbations are large. In this paper, we propose EdgeFool, an adversarial image enhancement filter that learns structure-aware adversarial perturbations. EdgeFool generates adversarial images with perturbations that enhance image details via training a fully convolutional neural network end-to-end with a multi-task loss function. This loss function accou…
It is important to extract good features using an encoder to realize semantic segmentation with high accuracy. Although loss function is optimized in training deep neural network, far layers from the layers for computing loss function are difficult to train. Skip connection is effective for this problem but there are still far layers from the loss function. In this paper, we propose the Feature Random Enhancement Module which enhances the features randomly in only training. By emphasizing the features at far layers from loss function, we can train those layers well and the accuracy was improve…
In the past few decades, to reduce the risk of X-ray in computed tomography (CT), low-dose CT image denoising has attracted extensive attention from researchers, which has become an important research issue in the field of medical images. In recent years, with the rapid development of deep learning technology, many algorithms have emerged to apply convolutional neural networks to this task, achieving promising results. However, there are still some problems such as low denoising efficiency, over-smoothed result, etc. In this paper, we propose the Edge enhancement based Densely connected Convol…
Arbitrary style transfer generates an artistic image which combines the structure of a content image and the artistic style of the artwork by using only one trained network. The image representation used in this method contains content structure representation and the style patterns representation, which is usually the features representation of high-level in the pre-trained classification networks. However, the traditional classification networks were designed for classification which usually focus on high-level features and ignore other features. As the result, the stylized images distribute…
In this paper, we present a deep learning-based image processing technique for extraction of bone structures in chest radiographs using a U-Net FCNN. The U-Net was trained to accomplish the task in a fully supervised setting. To create the training image pairs, we employed simulated X-Ray or Digitally Reconstructed Radiographs (DRR), derived from 664 CT scans belonging to the LIDC-IDRI dataset. Using HU based segmentation of bone structures in the CT domain, a synthetic 2D "Bone x-ray" DRR is produced and used for training the network. For the reconstruction loss, we utilize two loss functions…
CLADE: Cycle Loss Augmented Degradation Enhancement for Unpaired Super-Resolution of Anisotropic Medical Images
University College London（伦敦大学学院）；Institute of Cardiovascular Science（心血管科学研究所）；Centre for Medical Imaging（医学影像中心）；Frimley Health NHS Trust（弗林利健康 NHS 信托基金）；UCL NHS Trust（伦敦大学学院 NHS 信托基金）
Image-to-image translation is an ill-posed problem as unique one-to-one mapping may not exist between the source and target images. Learning-based methods proposed in this context often evaluate the performance on test data that is similar to the training data, which may be impractical. This demands robust methods that can quantify uncertainty in the prediction for making informed decisions, especially for critical areas such as medical imaging. Recent works that employ conditional generative adversarial networks (GANs) have shown improved performance in learning photo-realistic image-to-image…
City University of Hong Kong（香港城市大学）；Meituan-Dianping Group（美团点评集团）；City University of Hong Kong Shenzhen Research Institute（香港城市大学深圳研究院）
Improving the aesthetic quality of images is challenging and eager for the public. To address this problem, most existing algorithms are based on supervised learning methods to learn an automatic photo enhancer for paired data, which consists of low-quality photos and corresponding expert-retouched versions. However, the style and characteristics of photos retouched by experts may not meet the needs or preferences of general users. In this paper, we present an unsupervised image enhancement generative adversarial network (UEGAN), which learns the corresponding image-to-image mapping from a set…
Feature-oriented Deep Learning Framework for Pulmonary Cone-beam CT (CBCT) Enhancement with Multi-task Customized Perceptual Loss
The Hong Kong Polytechnic University（香港理工大学）；Sun Yat-Sen University（中山大学）；Fourth Military Medical University（中国人民解放军空军军医大学）；Xijing Hospital（西京医院）；Queen Mary Hospital（玛丽医院）；Guangzhou University of Chinese Medicine（广州中医药大学）；Soochow University（苏州大学）
Hebei Key Laboratory for Electromagnetic Environmental Effects and Information Processing（河北省电磁环境效应与信息处理重点实验室）；Shijiazhuang Tiedao University（石家庄铁道大学）
Temporal convolutions have been the paradigm of choice in action segmentation, which enhances long-term receptive fields by increasing convolution layers. However, high layers cause the loss of local information necessary for frame recognition. To solve the above problem, a novel encoder-decoder structure is proposed in this paper, called Cross-Enhancement Transformer. Our approach can be effective learning of temporal structure representation with interactive self-attention mechanism. Concatenated each layer convolutional feature maps in encoder with a set of features in decoder produced via …
Face-swapping models have been drawing attention for their compelling generation quality, but their complex architectures and loss functions often require careful tuning for successful training. We propose a new face-swapping model called `Smooth-Swap', which excludes complex handcrafted designs and allows fast and stable training. The main idea of Smooth-Swap is to build smooth identity embedding that can provide stable gradients for identity change. Unlike the one used in previous models trained for a purely discriminative task, the proposed embedding is trained with a supervised contrastive…
Existing deep learning (DL) based speech enhancement approaches are generally optimised to minimise the distance between clean and enhanced speech features. These often result in improved speech quality however they suffer from a lack of generalisation and may not deliver the required speech intelligibility in real noisy situations. In an attempt to address these challenges, researchers have explored intelligibility-oriented (I-O) loss functions and integration of audio-visual (AV) information for more robust speech enhancement (SE). In this paper, we introduce DL based I-O SE algorithms explo…
