Kaibing Zhang

Image Super-Resolution With Sparse Neighbor Embedding

Until now, neighbor-embedding-based (NE) algorithms for super-resolution (SR) have carried out two independent processes to synthesize high-resolution (HR) image patches. In the first process, neighbor search is performed using the Euclidean distance metric, and in the second process, the optimal weights are determined by solving a constrained least squares problem. However, the separate processes are not optimal. In this paper, we propose a sparse neighbor selection scheme for SR reconstruction. We first predetermine a larger number of neighbors as potential candidates and develop an extended Robust-SL0 algorithm to simultaneously find the neighbors and to solve the reconstruction weights. Recognizing that the k-nearest neighbor (k-NN) for reconstruction should have similar local geometric structures based on clustering, we employ a local statistical feature, namely histograms of oriented gradients (HoG) of low-resolution (LR) image patches, to perform such clustering. By conveying local structural information of HoG in the synthesis stage, the k-NN of each LR input patch is adaptively chosen from their associated subset, which significantly improves the speed of synthesizing the HR image while preserving the quality of reconstruction. Experimental results suggest that the proposed method can achieve competitive SR quality compared with other state-of-the-art baselines.

Joint Learning for Single-Image Super-Resolution via a Coupled Constraint

The neighbor-embedding (NE) algorithm for single-image super-resolution (SR) reconstruction assumes that the feature spaces of low-resolution (LR) and high-resolution (HR) patches are locally isometric. However, this is not true for SR because of one-to-many mappings between LR and HR patches. To overcome or at least to reduce the problem for NE-based SR reconstruction, we apply a joint learning technique to train two projection matrices simultaneously and to map the original LR and HR feature spaces onto a unified feature subspace. Subsequently, the k -nearest neighbor selection of the input LR image patches is conducted in the unified feature subspace to estimate the reconstruction weights. To handle a large number of samples, joint learning locally exploits a coupled constraint by linking the LR-HR counterparts together with the K-nearest grouping patch pairs. In order to refine further the initial SR estimate, we impose a global reconstruction constraint on the SR outcome based on the maximum a posteriori framework. Preliminary experiments suggest that the proposed algorithm outperforms NE-related baselines.

Learning Multiple Linear Mappings for Efficient Single Image Super-Resolution

Example learning-based superresolution (SR) algorithms show promise for restoring a high-resolution (HR) image from a single low-resolution (LR) input. The most popular approaches, however, are either time- or space-intensive, which limits their practical applications in many resource-limited settings. In this paper, we propose a novel computationally efficient single image SR method that learns multiple linear mappings (MLM) to directly transform LR feature subspaces into HR subspaces. In particular, we first partition the large nonlinear feature space of LR images into a cluster of linear subspaces. Multiple LR subdictionaries are then learned, followed by inferring the corresponding HR subdictionaries based on the assumption that the LR-HR features share the same representation coefficients. We establish MLM from the input LR features to the desired HR outputs in order to achieve fast yet stable SR recovery. Furthermore, in order to suppress displeasing artifacts generated by the MLM-based method, we apply a fast nonlocal means algorithm to construct a simple yet effective similarity-based regularization term for SR enhancement. Experimental results indicate that our approach is both quantitatively and qualitatively superior to other application-oriented SR methods, while maintaining relatively low time and space complexity.

Partially Supervised Neighbor Embedding for Example-Based Image Super-Resolution

Neighbor embedding algorithm has been widely used in example-based super-resolution reconstruction from a single frame, which makes the assumption that neighbor patches embedded are contained in a single manifold. However, it is not always true for complicated texture structure. In this paper, we believe that textures may be contained in multiple manifolds, corresponding to classes. Under this assumption, we present a novel example-based image super-resolution reconstruction algorithm with clustering and supervised neighbor embedding (CSNE). First, a class predictor for low-resolution (LR) patches is learnt by an unsupervised Gaussian mixture model. Then by utilizing class label information of each patch, a supervised neighbor embedding is used to estimate high-resolution (HR) patches corresponding to LR patches. The experimental results show that the proposed method can achieve a better recovery of LR comparing with other simple schemes using neighbor embedding.

Single Image Super-Resolution With Multiscale Similarity Learning

Example learning-based image super-resolution (SR) is recognized as an effective way to produce a high-resolution (HR) image with the help of an external training set. The effectiveness of learning-based SR methods, however, depends highly upon the consistency between the supporting training set and low-resolution (LR) images to be handled. To reduce the adverse effect brought by incompatible high-frequency details in the training set, we propose a single image SR approach by learning multiscale self-similarities from an LR image itself. The proposed SR approach is based upon an observation that small patches in natural images tend to redundantly repeat themselves many times both within the same scale and across different scales. To synthesize the missing details, we establish the HR-LR patch pairs using the initial LR input and its down-sampled version to capture the similarities across different scales and utilize the neighbor embedding algorithm to estimate the relationship between the LR and HR image pairs. To fully exploit the similarities across various scales inside the input LR image, we accumulate the previous resultant images as training examples for the subsequent reconstruction processes and adopt a gradual magnification scheme to upscale the LR input to the desired size step by step. In addition, to preserve sharper edges and suppress aliasing artifacts, we further apply the nonlocal means method to learn the similarity within the same scale and formulate a nonlocal prior regularization term to well pose SR estimation under a reconstruction-based SR framework. Experimental results demonstrate that the proposed method can produce compelling SR recovery both quantitatively and perceptually in comparison with other state-of-the-art baselines.

Multi-scale dictionary for single image super-resolution

Reconstruction- and example-based super-resolution (SR) methods are promising for restoring a high-resolution (HR) image from low-resolution (LR) image(s). Under large magnification, reconstruction-based methods usually fail to hallucinate visual details while example-based methods sometimes introduce unexpected details. Given a generic LR image, to reconstruct a photo-realistic SR image and to suppress artifacts in the reconstructed SR image, we introduce a multi-scale dictionary to a novel SR method that simultaneously integrates local and non-local priors. The local prior suppresses artifacts by using steering kernel regression to predict the target pixel from a small local area. The non-local prior enriches visual details by taking a weighted average of a large neighborhood as an estimate of the target pixel. Essentially, these two priors are complementary to each other. Experimental results demonstrate that the proposed method can produce high quality SR recovery both quantitatively and perceptually.

Zernike-Moment-Based Image Super Resolution

Multiframe super-resolution (SR) reconstruction aims to produce a high-resolution (HR) image using a set of low-resolution (LR) images. In the process of reconstruction, fuzzy registration usually plays a critical role. It mainly focuses on the correlation between pixels of the candidate and the reference images to reconstruct each pixel by averaging all its neighboring pixels. Therefore, the fuzzy-registration-based SR performs well and has been widely applied in practice. However, if some objects appear or disappear among LR images or different angle rotations exist among them, the correlation between corresponding pixels becomes weak. Thus, it will be difficult to use LR images effectively in the process of SR reconstruction. Moreover, if the LR images are noised, the reconstruction quality will be affected seriously. To address or at least reduce these problems, this paper presents a novel SR method based on the Zernike moment, to make the most of possible details in each LR image for high-quality SR reconstruction. Experimental results show that the proposed method outperforms existing methods in terms of robustness and visual effects.

A Unified Learning Framework for Single Image Super-Resolution

It has been widely acknowledged that learning- and reconstruction-based super-resolution (SR) methods are effective to generate a high-resolution (HR) image from a single low-resolution (LR) input. However, learning-based methods are prone to introduce unexpected details into resultant HR images. Although reconstruction-based methods do not generate obvious artifacts, they tend to blur fine details and end up with unnatural results. In this paper, we propose a new SR framework that seamlessly integrates learning- and reconstruction-based methods for single image SR to: 1) avoid unexpected artifacts introduced by learning-based SR and 2) restore the missing high-frequency details smoothed by reconstruction-based SR. This integrated framework learns a single dictionary from the LR input instead of from external images to hallucinate details, embeds nonlocal means filter in the reconstruction-based SR to enhance edges and suppress artifacts, and gradually magnifies the LR input to the desired high-quality SR result. We demonstrate both visually and quantitatively that the proposed framework produces better results than previous methods from the literature.

Similarity Constraints-Based Structured Output Regression Machine: An Approach to Image Super-Resolution

For regression-based single-image super-resolution (SR) problem, the key is to establish a mapping relation between high-resolution (HR) and low-resolution (LR) image patches for obtaining a visually pleasing quality image. Most existing approaches typically solve it by dividing the model into several single-output regression problems, which obviously ignores the circumstance that a pixel within an HR patch affects other spatially adjacent pixels during the training process, and thus tends to generate serious ringing artifacts in resultant HR image as well as increase computational burden. To alleviate these problems, we propose to use structured output regression machine (SORM) to simultaneously model the inherent spatial relations between the HR and LR patches, which is propitious to preserve sharp edges. In addition, to further improve the quality of reconstructed HR images, a nonlocal (NL) self-similarity prior in natural images is introduced to formulate as a regularization term to further enhance the SORM-based SR results. To offer a computation-effective SORM method, we use a relative small nonsupport vector samples to establish the accurate regression model and an accelerating algorithm for NL self-similarity calculation. Extensive SR experiments on various images indicate that the proposed method can achieve more promising performance than the other state-of-the-art SR methods in terms of both visual quality and computational cost.

Single-Image Super-Resolution Using Active-Sampling Gaussian Process Regression

As well known, Gaussian process regression (GPR) has been successfully applied to example learning-based image super-resolution (SR). Despite its effectiveness, the applicability of a GPR model is limited by its remarkably computational cost when a large number of examples are available to a learning task. For this purpose, we alleviate this problem of the GPR-based SR and propose a novel example learning-based SR method, called active-sampling GPR (AGPR). The newly proposed approach employs an active learning strategy to heuristically select more informative samples for training the regression parameters of the GPR model, which shows significant improvement on computational efficiency while keeping higher quality of reconstructed image. Finally, we suggest an accelerating scheme to further reduce the time complexity of the proposed AGPR-based SR by using a pre-learned projection matrix. We objectively and subjectively demonstrate that the proposed method is superior to other competitors for producing much sharper edges and finer details.