Measuring the similarity between patches in images is a fundamental building block in various tasks. Naturally, the patch-size has a major impact on the matching quality, and on the consequent application performance. Under the assumption that our patch database is sufficiently sampled, using large patches (e.g. 21-by-21) should be preferred over small ones (e.g. 7-by-7). However, this "dense-sampling" assumption is rarely true; in most cases large patches cannot find relevant nearby examples. This phenomenon is a consequence of the curse of dimensionality, stating that the database-size should grow exponentially with the patch-size to ensure proper matches. This explains the favored choice of small patch-size in most applications. Is there a way to keep the simplicity and work with small patches while getting some of the benefits that large patches provide? In this work we offer such an approach. We propose to concatenate the regular content of a conventional (small) patch with a compact representation of its (large) surroundings - its context. Therefore, with a minor increase of the dimensions (e.g. with additional 10 values to the patch representation), we implicitly/softly describe the information of a large patch. The additional descriptors are computed based on a self-similarity behavior of the patch surrounding. We show that this approach achieves better matches, compared to the use of conventional-size patches, without the need to increase the database-size. Also, the effectiveness of the proposed method is tested on three distinct problems: (i) External natural image denoising, (ii) Depth image super-resolution, and (iii) Motion-compensated frame-rate up-conversion.
In this paper, we propose a novel scheme for scalable image coding based on the concept of epitome. An epitome can be seen as a factorized representation of an image. Focusing on spatial scalability, the enhancement layer of the proposed scheme contains only the epitome of the input image. The pixels of the enhancement layer not contained in the epitome are then restored using two approaches inspired from local learning-based super-resolution methods. In the first method, a locally linear embedding model is learned on base layer patches and then applied to the corresponding epitome patches to reconstruct the enhancement layer. The second approach learns linear mappings between pairs of co-located base layer and epitome patches. Experiments have shown that significant improvement of the rate-distortion performances can be achieved compared to an SHVC reference.
Depth image super-resolution is an extremely challenging task due to the information loss in sub-sampling. Deep convolutional neural network have been widely applied to color image super-resolution. Quite surprisingly, this success has not been matched to depth super-resolution. This is mainly due to the inherent difference between color and depth images. In this paper, we bridge up the gap and extend the success of deep convolutional neural network to depth super-resolution. The proposed deep depth super-resolution method learns the mapping from a low-resolution depth image to a high resolution one in an end-to-end style. Furthermore, to better regularize the learned depth map, we propose to exploit the depth field statistics and the local correlation between depth image and color image. These priors are integrated in an energy minimization formulation, where the deep neural network learns the unary term, the depth field statistics works as global model constraint and the color-depth correlation is utilized to enforce the local structure in depth images. Extensive experiments on various depth super-resolution benchmark datasets show that our method outperforms the state-of-the-art depth image super-resolution methods with a margin.
In this work, we consider the image super-resolution (SR) problem. The main challenge of image SR is to recover high-frequency details of a low-resolution (LR) image that are important for human perception. To address this essentially ill-posed problem, we introduce a Deep Edge Guided REcurrent rEsidual~(DEGREE) network to progressively recover the high-frequency details. Different from most of existing methods that aim at predicting high-resolution (HR) images directly, DEGREE investigates an alternative route to recover the difference between a pair of LR and HR images by recurrent residual learning. DEGREE further augments the SR process with edge-preserving capability, namely the LR image and its edge map can jointly infer the sharp edge details of the HR image during the recurrent recovery process. To speed up its training convergence rate, by-pass connections across multiple layers of DEGREE are constructed. In addition, we offer an understanding on DEGREE from the view-point of sub-band frequency decomposition on image signal and experimentally demonstrate how DEGREE can recover different frequency bands separately. Extensive experiments on three benchmark datasets clearly demonstrate the superiority of DEGREE over well-established baselines and DEGREE also provides new state-of-the-arts on these datasets.
Also recently, exciting strides forward have been made in the area of image restoration, particularly for image denoising and single image super-resolution. Deep learning techniques contributed to this significantly. The top methods differ in their formulations and assumptions, so even if their average performance may be similar, some work better on certain image types and image regions than others. This complementarity motivated us to propose a novel 3D convolutional fusion (3DCF) method. Unlike other methods adapted to different tasks, our method uses the exact same convolutional network architecture to address both image denois- ing and single image super-resolution. As a result, our 3DCF method achieves substantial improvements (0.1dB-0.4dB PSNR) over the state-of-the-art methods that it fuses, and this on standard benchmarks for both tasks. At the same time, the method still is computationally efficient.
Recently, machine learning based single image super resolution (SR) approaches focus on jointly learning representations for high-resolution (HR) and low-resolution (LR) image patch pairs to improve the quality of the super-resolved images. However, due to treat all image pixels equally without considering the salient structures, these approaches usually fail to produce visual pleasant images with sharp edges and fine details. To address this issue, in this work we present a new novel SR approach, which replaces the main building blocks of the classical interpolation pipeline by a flexible, content-adaptive deep neural networks. In particular, two well-designed structure-aware components, respectively capturing local- and holistic- image contents, are naturally incorporated into the fully-convolutional representation learning to enhance the image sharpness and naturalness. Extensively evaluations on several standard benchmarks (e.g., Set5, Set14 and BSD200) demonstrate that our approach can achieve superior results, especially on the image with salient structures, over many existing state-of-the-art SR methods under both quantitative and qualitative measures.
In this paper we present a novel method to increase the spatial resolution of depth images. We combine a deep fully convolutional network with a non-local variational method in a deep primal-dual network. The joint network computes a noise-free, high-resolution estimate from a noisy, low-resolution input depth map. Additionally, a high-resolution intensity image is used to guide the reconstruction in the network. By unrolling the optimization steps of a first-order primal-dual algorithm and formulating it as a network, we can train our joint method end-to-end. This not only enables us to learn the weights of the fully convolutional network, but also to optimize all parameters of the variational method and its optimization procedure. The training of such a deep network requires a large dataset for supervision. Therefore, we generate high-quality depth maps and corresponding color images with a physically based renderer. In an exhaustive evaluation we show that our method outperforms the state-of-the-art on multiple benchmarks.
In this work we present a novel approach for single depth map super-resolution. Modern consumer depth sensors, especially Time-of-Flight sensors, produce dense depth measurements, but are affected by noise and have a low lateral resolution. We propose a method that combines the benefits of recent advances in machine learning based single image super-resolution, i.e. deep convolutional networks, with a variational method to recover accurate high-resolution depth maps. In particular, we integrate a variational method that models the piecewise affine structures apparent in depth data via an anisotropic total generalized variation regularization term on top of a deep network. We call our method ATGV-Net and train it end-to-end by unrolling the optimization procedure of the variational method. To train deep networks, a large corpus of training data with accurate ground-truth is required. We demonstrate that it is feasible to train our method solely on synthetic data that we generate in large quantities for this task. Our evaluations show that we achieve state-of-the-art results on three different benchmarks, as well as on a challenging Time-of-Flight dataset, all without utilizing an additional intensity image as guidance.
One impressive advantage of convolutional neural networks (CNNs) is their ability to automatically learn feature representation from raw pixels, eliminating the need for hand-designed procedures. However, recent methods for single image super-resolution (SR) fail to maintain this advantage. They utilize CNNs in two decoupled steps, i.e., first upsampling the low resolution (LR) image to the high resolution (HR) size with hand-designed techniques (e.g., bicubic interpolation), and then applying CNNs on the upsampled LR image to reconstruct HR results. In this paper, we seek an alternative and propose a new image SR method, which jointly learns the feature extraction, upsampling and HR reconstruction modules, yielding a completely end-to-end trainable deep CNN. As opposed to existing approaches, the proposed method conducts upsampling in the latent feature space with filters that are optimized for the task of image SR. In addition, the HR reconstruction is performed in a multi-scale manner to simultaneously incorporate both short- and long-range contextual information, ensuring more accurate restoration of HR images. To facilitate network training, a new training approach is designed, which jointly trains the proposed deep network with a relatively shallow network, leading to faster convergence and more superior performance. The proposed method is extensively evaluated on widely adopted data sets and improves the performance of state-of-the-art methods with a considerable margin. Moreover, in-depth ablation studies are conducted to verify the contribution of different network designs to image SR, providing additional insights for future research.
As a successful deep model applied in image super-resolution (SR), the Super-Resolution Convolutional Neural Network (SRCNN) has demonstrated superior performance to the previous hand-crafted models either in speed and restoration quality. However, the high computational cost still hinders it from practical usage that demands real-time performance (24 fps). In this paper, we aim at accelerating the current SRCNN, and propose a compact hourglass-shape CNN structure for faster and better SR. We re-design the SRCNN structure mainly in three aspects. First, we introduce a deconvolution layer at the end of the network, then the mapping is learned directly from the original low-resolution image (without interpolation) to the high-resolution one. Second, we reformulate the mapping layer by shrinking the input feature dimension before mapping and expanding back afterwards. Third, we adopt smaller filter sizes but more mapping layers. The proposed model achieves a speed up of more than 40 times with even superior restoration quality. Further, we present the parameter settings that can achieve real-time performance on a generic CPU while still maintaining good performance. A corresponding transfer strategy is also proposed for fast training and testing across different upscaling factors.
This paper describes a novel projection algorithm, the Projection Onto Span Algorithm (POSA) for wavelet-based superresolution and removing speckle (in wavelet domain) of unknown variance from Synthetic Aperture Radar (SAR) images. Although the POSA is good as a new superresolution algorithm for image enhancement, image metrology and biometric identification, here one will use it like a tool of despeckling, being the first time that an algorithm of super-resolution is used for despeckling of SAR images. Specifically, the speckled SAR image is decomposed into wavelet subbands, POSA is applied to the high subbands, and reconstruct a SAR image from the modified detail coefficients. Experimental results demonstrate that the new method compares favorably to several other despeckling methods on test SAR images.
Discriminative model learning for image denoising has been recently attracting considerable attentions due to its favorable denoising performance. In this paper, we take one step forward by investigating the construction of feed-forward denoising convolutional neural networks (DnCNNs) to embrace the progress in very deep architecture, learning algorithm, and regularization method into image denoising. Specifically, residual learning and batch normalization are utilized to speed up the training process as well as boost the denoising performance. Different from the existing discriminative denoising models which usually train a specific model for additive white Gaussian noise (AWGN) at a certain noise level, our DnCNN model is able to handle Gaussian denoising with unknown noise level (i.e., blind Gaussian denoising). With the residual learning strategy, DnCNN implicitly removes the latent clean image in the hidden layers. This property motivates us to train a single DnCNN model to tackle with several general image denoising tasks such as Gaussian denoising, single image super-resolution and JPEG image deblocking. Our extensive experiments demonstrate that our DnCNN model can not only exhibit high effectiveness in several general image denoising tasks, but also be efficiently implemented by benefiting from GPU computing.
Image restoration is a long-standing problem in low-level computer vision with many interesting applications. We describe a flexible learning framework based on the concept of nonlinear reaction diffusion models for various image restoration problems. By embodying recent improvements in nonlinear diffusion models, we propose a dynamic nonlinear reaction diffusion model with time-dependent parameters (\ie, linear filters and influence functions). In contrast to previous nonlinear diffusion models, all the parameters, including the filters and the influence functions, are simultaneously learned from training data through a loss based approach. We call this approach TNRD -- \textit{Trainable Nonlinear Reaction Diffusion}. The TNRD approach is applicable for a variety of image restoration tasks by incorporating appropriate reaction force. We demonstrate its capabilities with three representative applications, Gaussian image denoising, single image super resolution and JPEG deblocking. Experiments show that our trained nonlinear diffusion models largely benefit from the training of the parameters and finally lead to the best reported performance on common test datasets for the tested applications. Our trained models preserve the structural simplicity of diffusion models and take only a small number of diffusion steps, thus are highly efficient. Moreover, they are also well-suited for parallel computation on GPUs, which makes the inference procedure extremely fast.
Image restoration, including image denoising, super resolution, inpainting, and so on, is a well-studied problem in computer vision and image processing, as well as a test bed for low-level image modeling algorithms. In this work, we propose a very deep fully convolutional auto-encoder network for image restoration, which is a encoding-decoding framework with symmetric convolutional-deconvolutional layers. In other words, the network is composed of multiple layers of convolution and de-convolution operators, learning end-to-end mappings from corrupted images to the original ones. The convolutional layers capture the abstraction of image contents while eliminating corruptions. Deconvolutional layers have the capability to upsample the feature maps and recover the image details. To deal with the problem that deeper networks tend to be more difficult to train, we propose to symmetrically link convolutional and deconvolutional layers with skip-layer connections, with which the training converges much faster and attains better results.
Context: in large-scale spatial surveys, the Point Spread Function (PSF) varies across the instrument field of view (FOV). Local measurements of the PSFs are given by the isolated stars images. Yet, these estimates may not be directly usable for post-processings because of the observational noise and potentially the aliasing. Aims: given a set of aliased and noisy stars images from a telescope, we want to estimate well-resolved and noise-free PSFs at the observed stars positions, in particular, exploiting the spatial correlation of the PSFs across the FOV. Contributions: we introduce RCA (Resolved Components Analysis) which is a noise-robust dimension reduction and super-resolution method based on matrix factorization. We propose an original way of using the PSFs spatial correlation in the restoration process through sparsity. The introduced formalism can be applied to correlated data sets with respect to any euclidean parametric space. Results: we tested our method on simulated monochromatic PSFs of Euclid telescope (launch planned for 2020). The proposed method outperforms existing PSFs restoration and dimension reduction methods. We show that a coupled sparsity constraint on individual PSFs and their spatial distribution yields a significant improvement on both the restored PSFs shapes and the PSFs subspace identification, in presence of aliasing. Perspectives: RCA can be naturally extended to account for the wavelength dependency of the PSFs.
In this paper, we propose a very deep fully convolutional encoding-decoding framework for image restoration such as denoising and super-resolution. The network is composed of multiple layers of convolution and de-convolution operators, learning end-to-end mappings from corrupted images to the original ones. The convolutional layers act as the feature extractor, which capture the abstraction of image contents while eliminating noises/corruptions. De-convolutional layers are then used to recover the image details. We propose to symmetrically link convolutional and de-convolutional layers with skip-layer connections, with which the training converges much faster and attains a higher-quality local optimum. First, The skip connections allow the signal to be back-propagated to bottom layers directly, and thus tackles the problem of gradient vanishing, making training deep networks easier and achieving restoration performance gains consequently. Second, these skip connections pass image details from convolutional layers to de-convolutional layers, which is beneficial in recovering the original image. Significantly, with the large capacity, we can handle different levels of noises using a single model. Experimental results show that our network achieves better performance than all previously reported state-of-the-art methods.
Motion estimation across low-resolution frames and the reconstruction of high-resolution images are two coupled subproblems of multi-frame super-resolution. This paper introduces a new joint optimization approach for motion estimation and image reconstruction to address this interdependence. Our method is formulated via non-linear least squares optimization and combines two principles of robust super-resolution. First, to enhance the robustness of the joint estimation, we propose a confidence-aware energy minimization framework augmented with sparse regularization. Second, we develop a tailor-made Levenberg-Marquardt iteration scheme to jointly estimate motion parameters and the high-resolution image along with the corresponding model confidence parameters. Our experiments on simulated and real images confirm that the proposed approach outperforms decoupled motion estimation and image reconstruction as well as related state-of-the-art joint estimation algorithms.
Transport-based techniques for signal and data analysis have received increased attention recently. Given their abilities to provide accurate generative models for signal intensities and other data distributions, they have been used in a variety of applications including content-based retrieval, cancer detection, image super-resolution, and statistical machine learning, to name a few, and shown to produce state of the art in several applications. Moreover, the geometric characteristics of transport-related metrics have inspired new kinds of algorithms for interpreting the meaning of data distributions. Here we provide an overview of the mathematical underpinnings of mass transport-related methods, including numerical implementation, as well as a review, with demonstrations, of several applications.
Segmentation, a useful/powerful technique in pattern recognition, is the process of identifying object outlines within images. There are a number of efficient algorithms for segmentation in Euclidean space that depend on the variational approach and partial differential equation modelling. Wavelets have been used successfully in various problems in image processing, including segmentation, inpainting, noise removal, super-resolution image restoration, and many others. Wavelets on the sphere have been developed to solve such problems for data defined on the sphere, which arise in numerous fields such as cosmology and geophysics. In this work, we propose a wavelet-based method to segment images on the sphere, accounting for the underlying geometry of spherical data. Our method is a direct extension of the tight-frame based segmentation method used to automatically identify tube-like structures such as blood vessels in medical imaging. It is compatible with any arbitrary type of wavelet frame defined on the sphere, such as axisymmetric wavelets, directional wavelets, curvelets, and hybrid wavelet constructions. Such an approach allows the desirable properties of wavelets to be naturally inherited in the segmentation process. In particular, directional wavelets and curvelets, which were designed to efficiently capture directional signal content, provide additional advantages in segmenting images containing prominent directional and curvilinear features. We present several numerical experiments, applying our wavelet-based segmentation method, as well as the common K-means method, on real-world spherical images. These experiments demonstrate the superiority of our method and show that it is capable of segmenting different kinds of spherical images, including those with prominent directional features. Moreover, our algorithm is efficient with convergence usually within a few iterations.
Recently, several models based on deep neural networks have achieved great success in terms of both reconstruction accuracy and computational performance for single image super-resolution. In these methods, the low resolution (LR) input image is upscaled to the high resolution (HR) space using a single filter, commonly bicubic interpolation, before reconstruction. This means that the super-resolution (SR) operation is performed in HR space. We demonstrate that this is sub-optimal and adds computational complexity. In this paper, we present the first convolutional neural network (CNN) capable of real-time SR of 1080p videos on a single K2 GPU. To achieve this, we propose a novel CNN architecture where the feature maps are extracted in the LR space. In addition, we introduce an efficient sub-pixel convolution layer which learns an array of upscaling filters to upscale the final LR feature maps into the HR output. By doing so, we effectively replace the handcrafted bicubic filter in the SR pipeline with more complex upscaling filters specifically trained for each feature map, whilst also reducing the computational complexity of the overall SR operation. We evaluate the proposed approach using images and videos from publicly available datasets and show that it performs significantly better (+0.15dB on Images and +0.39dB on Videos) and is an order of magnitude faster than previous CNN-based methods.