Abstract—Single image super-resolution (SR) is an ill-posed problem, which tries to recover a high-resolution image from its low-resolution observation. To regularize the solution of the problem, previousmethods have focused on designing good priors for natural images, such as sparse representation, or directly learning the priors from a large data set with models, such as deep neural networks. In this paper, we argue that domain expertise from the conventional sparse coding model can be combined with the key ingredients of deep learning to achieve further improved results. We demonstrate that a sparse coding model particularly designed for SR can be incarnated as a neural network with the merit of end-to-end optimization over training data. The network has a cascaded structure, which boosts the SR performance for both fixed and incremental scaling factors. The proposed training and testing schemes can be extended for robust handling of images with additional degradation, such as noise and blurring. A subjective assessment is conducted and analyzed in order to thoroughly evaluate various SR techniques. Our proposed model is tested on a wide range of images, and it significantly outperforms the existing state-of-the-art methods for various scaling factors both quantitatively and perceptually. Index Terms—Image super-resolution, deep neural networks, sparse coding.
In this work, very deep super-resolution (VDSR) method is presented for improving the spatial resolution of remotely sensed (RS) images for scale factor 4. The VDSR net is re-trained with Sentinel-2 images and with drone aero orthophoto images, thus becomes RS-VDSR and Aero-VDSR, respectively. A novel loss function, the Var-norm estimator, is proposed in the regression layer of the convolutional neural network during re-training and prediction. According to numerical and optical comparisons, the proposed nets RS-VDSR and Aero-VDSR can outperform VDSR during prediction with RS images. RS-VDSR outperforms VDSR up to 3.16 dB in terms of PSNR in Sentinel-2 images.
In this work, we propose a Neural Architecture Search (NAS) for retinal layer segmentation in Optical Coherence Tomography (OCT) scans. We incorporate the Unet architecture in the NAS framework as its backbone for the segmentation of the retinal layers in our collected and pre-processed OCT image dataset. At the pre-processing stage, we conduct super resolution and image processing techniques on the raw OCT scans to improve the quality of the raw images. For our search strategy, different primitive operations are suggested to find the down- & up-sampling cell blocks, and the binary gate method is applied to make the search strategy practical for the task in hand. We empirically evaluated our method on our in-house OCT dataset. The experimental results demonstrate that the self-adapting NAS-Unet architecture substantially outperformed the competitive human-designed architecture by achieving 95.4% in mean Intersection over Union metric and 78.7% in Dice similarity coefficient.
It has recently been demonstrated that spatial resolution adaptation can be integrated within video compression to improve overall coding performance by spatially down-sampling before encoding and super-resolving at the decoder. Significant improvements have been reported when convolutional neural networks (CNNs) were used to perform the resolution up-sampling. However, this approach suffers from high complexity at the decoder due to the employment of CNN-based super-resolution. In this paper, a novel framework is proposed which supports the flexible allocation of complexity between the encoder and decoder. This approach employs a CNN model for video down-sampling at the encoder and uses a Lanczos3 filter to reconstruct full resolution at the decoder. The proposed method was integrated into the HEVC HM 16.20 software and evaluated on JVET UHD test sequences using the All Intra configuration. The experimental results demonstrate the potential of the proposed approach, with significant bitrate savings (more than 10%) over the original HEVC HM, coupled with reduced computational complexity at both encoder (29%) and decoder (10%).
Accurate lung lesion segmentation from Computed Tomography (CT) images is crucial to the analysis and diagnosis of lung diseases such as COVID-19 and lung cancer. However, the smallness and variety of lung nodules and the lack of high-quality labeling make the accurate lung nodule segmentation difficult. To address these issues, we first introduce a novel segmentation mask named Soft Mask which has richer and more accurate edge details description and better visualization and develop a universal automatic Soft Mask annotation pipeline to deal with different datasets correspondingly. Then, a novel Network with detailed representation transfer and Soft Mask supervision (DSNet) is proposed to process the input low-resolution images of lung nodules into high-quality segmentation results. Our DSNet contains a special Detail Representation Transfer Module (DRTM) for reconstructing the detailed representation to alleviate the small size of lung nodules images, and an adversarial training framework with Soft Mask for further improving the accuracy of segmentation. Extensive experiments validate that our DSNet outperforms other state-of-the-art methods for accurate lung nodule segmentation and has strong generalization ability in other accurate medical segmentation tasks with competitive results. Besides, we provide a new challenging lung nodules segmentation dataset for further studies.
Due to the limitations of hyperspectral imaging systems, hyperspectral imagery (HSI) often suffers from poor spatial resolution, thus hampering many applications of the imagery. Hyperspectral super-resolution refers to fusing HSI and MSI to generate an image with both high spatial and high spectral resolutions. Recently, several new methods have been proposed to solve this fusion problem, and most of these methods assume that the prior information of the Point Spread Function (PSF) and Spectral Response Function (SRF) are known. However, in practice, this information is often limited or unavailable. In this work, an unsupervised deep learning-based fusion method - HyCoNet - that can solve the problems in HSI-MSI fusion without the prior PSF and SRF information is proposed. HyCoNet consists of three coupled autoencoder nets in which the HSI and MSI are unmixed into endmembers and abundances based on the linear unmixing model. Two special convolutional layers are designed to act as a bridge that coordinates with the three autoencoder nets, and the PSF and SRF parameters are learned adaptively in the two convolution layers during the training process. Furthermore, driven by the joint loss function, the proposed method is straightforward and easily implemented in an end-to-end training manner. The experiments performed in the study demonstrate that the proposed method performs well and produces robust results for different datasets and arbitrary PSFs and SRFs.
In recent years, deep learning has made great progress in many fields such as image recognition, natural language processing, speech recognition and video super-resolution. In this survey, we comprehensively investigate 33 state-of-the-art video super-resolution (VSR) methods based on deep learning. It is well known that the leverage of information within video frames is important for video super-resolution. Thus we propose a taxonomy and classify the methods into six sub-categories according to the ways of utilizing inter-frame information. Moreover, the architectures and implementation details of all the methods are depicted in detail. Finally, we summarize and compare the performance of the representative VSR method on some benchmark datasets. We also discuss some challenges, which need to be further addressed by researchers in the community of VSR. To the best of our knowledge, this work is the first systematic review on VSR tasks, and it is expected to make a contribution to the development of recent studies in this area and potentially deepen our understanding to the VSR techniques based on deep learning.
Prior probability models are a fundamental component of many image processing problems, but density estimation is notoriously difficult for high-dimensional signals such as photographic images. Deep neural networks have provided state-of-the-art solutions for problems such as denoising, which implicitly rely on a prior probability model of natural images. Here, we develop a robust and general methodology for making use of this implicit prior. We rely on a statistical result due to Miyasawa (1961), who showed that the least-squares solution for removing additive Gaussian noise can be written directly in terms of the gradient of the log of the noisy signal density. We use this fact to develop a stochastic coarse-to-fine gradient ascent procedure for drawing high-probability samples from the implicit prior embedded within a CNN trained to perform blind (i.e., with unknown noise level) least-squares denoising. A generalization of this algorithm to constrained sampling provides a method for using the implicit prior to solve any linear inverse problem, with no additional training. We demonstrate this general form of transfer learning in multiple applications, using the same algorithm to produce state-of-the-art levels of unsupervised performance for deblurring, super-resolution, inpainting, and compressive sensing.
Mobile microscopy is a promising technology to assist and to accelerate disease diagnostics, with its widespread adoption being hindered by the mediocre quality of acquired images. Although some paired image translation and super-resolution approaches for mobile microscopy have emerged, a set of essential challenges, necessary for automating it in a high-throughput setting, still await to be addressed. The issues like in-focus/out-of-focus classification, fast scanning deblurring, focus-stacking, etc. -- all have specific peculiarities when the data are recorded using a mobile device. In this work, we aspire to create a comprehensive pipeline by connecting a set of methods purposely tuned to mobile microscopy: (1) a CNN model for stable in-focus / out-of-focus classification, (2) modified DeblurGAN architecture for image deblurring, (3) FuseGAN model for combining in-focus parts from multiple images to boost the detail. We discuss the limitations of the existing solutions developed for professional clinical microscopes, propose corresponding improvements, and compare to the other state-of-the-art mobile analytics solutions.
3D human shape and pose estimation from monocular images has been an active area of research in computer vision, having a substantial impact on the development of new applications, from activity recognition to creating virtual avatars. Existing deep learning methods for 3D human shape and pose estimation rely on relatively high-resolution input images; however, high-resolution visual content is not always available in several practical scenarios such as video surveillance and sports broadcasting. Low-resolution images in real scenarios can vary in a wide range of sizes, and a model trained in one resolution does not typically degrade gracefully across resolutions. Two common approaches to solve the problem of low-resolution input are applying super-resolution techniques to the input images which may result in visual artifacts, or simply training one model for each resolution, which is impractical in many realistic applications. To address the above issues, this paper proposes a novel algorithm called RSC-Net, which consists of a Resolution-aware network, a Self-supervision loss, and a Contrastive learning scheme. The proposed network is able to learn the 3D body shape and pose across different resolutions with a single model. The self-supervision loss encourages scale-consistency of the output, and the contrastive learning scheme enforces scale-consistency of the deep features. We show that both these new training losses provide robustness when learning 3D shape and pose in a weakly-supervised manner. Extensive experiments demonstrate that the RSC-Net can achieve consistently better results than the state-of-the-art methods for challenging low-resolution images.
We introduce Frequency Domain Perceptual Loss (FDPL), a loss function for single image super resolution (SR). Unlike previous loss functions used to train SR models, which are all calculated in the pixel (spatial) domain, FDPL is computed in the frequency domain. By working in the frequency domain we can encourage a given model to learn a mapping that prioritizes those frequencies most related to human perception. While the goal of FDPL is not to maximize the Peak Signal to Noise Ratio (PSNR), we found that there is a correlation between decreasing FDPL and increasing PSNR. Training a model with FDPL results in a higher average PSRN (30.94), compared to the same model trained with pixel loss (30.59), as measured on the Set5 image dataset. We also show that our method achieves higher qualitative results, which is the goal of a perceptual loss function. However, it is not clear that the improved perceptual quality is due to the slightly higher PSNR or the perceptual nature of FDPL.
Image quality assessment (IQA) is the key factor for the fast development of image restoration (IR) algorithms. The most recent IR methods based on Generative Adversarial Networks (GANs) have achieved significant improvement in visual performance, but also presented great challenges for quantitative evaluation. Notably, we observe an increasing inconsistency between perceptual quality and the evaluation results. Then we raise two questions: (1) Can existing IQA methods objectively evaluate recent IR algorithms? (2) When focus on beating current benchmarks, are we getting better IR algorithms? To answer these questions and promote the development of IQA methods, we contribute a large-scale IQA dataset, called Perceptual Image Processing Algorithms (PIPAL) dataset. Especially, this dataset includes the results of GAN-based methods, which are missing in previous datasets. We collect more than 1.13 million human judgments to assign subjective scores for PIPAL images using the more reliable "Elo system". Based on PIPAL, we present new benchmarks for both IQA and super-resolution methods. Our results indicate that existing IQA methods cannot fairly evaluate GAN-based IR algorithms. While using appropriate evaluation methods is important, IQA methods should also be updated along with the development of IR algorithms. At last, we improve the performance of IQA networks on GAN-based distortions by introducing anti-aliasing pooling. Experiments show the effectiveness of the proposed method.
Video super-resolution (VSR) aims to utilize multiple low-resolution frames to generate a high-resolution prediction for each frame. In this process, inter- and intra-frames are the key sources for exploiting temporal and spatial information. However, there are a couple of limitations for existing VSR methods. First, optical flow is often used to establish temporal correspondence. But flow estimation itself is error-prone and affects recovery results. Second, similar patterns existing in natural images are rarely exploited for the VSR task. Motivated by these findings, we propose a temporal multi-correspondence aggregation strategy to leverage similar patches across frames, and a cross-scale nonlocal-correspondence aggregation scheme to explore self-similarity of images across scales. Based on these two new modules, we build an effective multi-correspondence aggregation network (MuCAN) for VSR. Our method achieves state-of-the-art results on multiple benchmark datasets. Extensive experiments justify the effectiveness of our method.
In this paper we deal with contour detection based on the recent image analogy principle which has been successfully used for super-resolution, texture and curves synthesis and interactive editing. Hand-drawn outlines are initially as benchmarks. Given such a reference image, we present a new method based on this expertise to locate contours of a query image in the same way that it is done for the reference (i.e by analogy). Applying a image analogies for contour detection using hand drawn images as leaning images cannot gives good result for any query image. The contour detection may be improved if we increase the number of learning images such that there will be exist similarity between query image and some reference images. In addition of the hardness of contours drawing task, this will increase considerably the time computation. We investigated in this work, how can we avoid this constraint in order to guaranty that all contour pixels will be located for any query image. Fourteen derived stereo patches, derived from a mathematical study, are the knowledge used in order to locate contours at different scales independently of the light conditions. Comprehensive experiments are conducted on different data sets (BSD 500, Horses of Weizmann). The obtained results show superior performance via precision and recall vs. hand-drawn contours at multiple resolutions to the reported state of the art.
Video super-resolution, which aims at producing a high-resolution video from its corresponding low-resolution version, has recently drawn increasing attention. In this work, we propose a novel method that can effectively incorporate temporal information in a hierarchical way. The input sequence is divided into several groups, with each one corresponding to a kind of frame rate. These groups provide complementary information to recover missing details in the reference frame, which is further integrated with an attention module and a deep intra-group fusion module. In addition, a fast spatial alignment is proposed to handle videos with large motion. Extensive results demonstrate the capability of the proposed model in handling videos with various motion. It achieves favorable performance against state-of-the-art methods on several benchmark datasets.
State-of-the-art face super-resolution methods employ deep convolutional neural networks to learn a mapping between low- and high- resolution facial patterns by exploring local appearance knowledge. However, most of these methods do not well exploit facial structures and identity information, and struggle to deal with facial images that exhibit large pose variations. In this paper, we propose a novel face super-resolution method that explicitly incorporates 3D facial priors which grasp the sharp facial structures. Our work is the first to explore 3D morphable knowledge based on the fusion of parametric descriptions of face attributes (e.g., identity, facial expression, texture, illumination, and face pose). Furthermore, the priors can easily be incorporated into any network and are extremely efficient in improving the performance and accelerating the convergence speed. Firstly, a 3D face rendering branch is set up to obtain 3D priors of salient facial structures and identity knowledge. Secondly, the Spatial Attention Module is used to better exploit this hierarchical information (i.e., intensity similarity, 3D facial structure, and identity content) for the super-resolution problem. Extensive experiments demonstrate that the proposed 3D priors achieve superior face super-resolution results over the state-of-the-arts.
Multi-scale design has been considered in recent image super-resolution (SR) works to explore the hierarchical feature information. Existing multi-scale networks aim to build elaborate blocks or progressive architecture for restoration. In general, larger scale features concentrate more on structural and high-level information, while smaller scale features contain plentiful details and textured information. In this point of view, information from larger scale features can be derived from smaller ones. Based on the observation, in this paper, we build a sequential hierarchical learning super-resolution network (SHSR) for effective image SR. Specially, we consider the inter-scale correlations of features, and devise a sequential multi-scale block (SMB) to progressively explore the hierarchical information. SMB is designed in a recursive way based on the linearity of convolution with restricted parameters. Besides the sequential hierarchical learning, we also investigate the correlations among the feature maps and devise a distribution transformation block (DTB). Different from attention-based methods, DTB regards the transformation in a normalization manner, and jointly considers the spatial and channel-wise correlations with scaling and bias factors. Experiment results show SHSR achieves superior quantitative performance and visual quality to state-of-the-art methods with near 34\% parameters and 50\% MACs off when scaling factor is $\times4$. To boost the performance without further training, the extension model SHSR$^+$ with self-ensemble achieves competitive performance than larger networks with near 92\% parameters and 42\% MACs off with scaling factor $\times4$.
Imaging of scenes using light or other wave phenomena is subject to the diffraction limit. The spatial profile of a wave propagating between a scene and the imaging system is distorted by diffraction resulting in a loss of resolution that is proportional with traveled distance. We show here that it is possible to reconstruct sparse scenes from the temporal profile of the wave-front using only one spatial pixel or a spatial average. The temporal profile of the wave is not affected by diffraction yielding an imaging method that can in theory achieve wavelength scale resolution independent of distance from the scene.
Human pose estimation (HPE) is a key building block for developing AI-based context-aware systems inside the operating room (OR). The 24/7 use of images coming from cameras mounted on the OR ceiling can however raise concerns for privacy, even in the case of depth images captured by RGB-D sensors. Being able to solely use low-resolution privacy-preserving images would address these concerns and help scale up the computer-assisted approaches that rely on such data to a larger number of ORs. In this paper, we introduce the problem of HPE on low-resolution depth images and propose an end-to-end solution that integrates a multi-scale super-resolution network with a 2D human pose estimation network. By exploiting intermediate feature-maps generated at different super-resolution, our approach achieves body pose results on low-resolution images (of size 64x48) that are on par with those of an approach trained and tested on full resolution images (of size 640x480).
With extremely high temporal resolution, event cameras have a large potential for robotics and computer vision. However, their asynchronous imaging mechanism often aggravates the measurement sensitivity to noises and brings a physical burden to increase the image spatial resolution. To recover high-quality intensity images, one should address both denoising and super-resolution problems for event cameras. Since events depict brightness changes, with the enhanced degeneration model by the events, the clear and sharp high-resolution latent images can be recovered from the noisy, blurry and low-resolution intensity observations. Exploiting the framework of sparse learning, the events and the low-resolution intensity observations can be jointly considered. Based on this, we propose an explainable network, an event-enhanced sparse learning network (eSL-Net), to recover the high-quality images from event cameras. After training with a synthetic dataset, the proposed eSL-Net can largely improve the performance of the state-of-the-art by 7-12 dB. Furthermore, without additional training process, the proposed eSL-Net can be easily extended to generate continuous frames with frame-rate as high as the events.