Defocus blur, common in shallow depth-of-field photography, varies across image regions and is challenging to accurately estimate and restore. Existing deblurring methods often struggle to capture fine structural textures and do not effectively adapt to regional differences in blur. We propose Multi-Level Blur-Aware Stable Diffusion (MBSD), a novel framework that explicitly integrates regional blur recognition into a diffusion-based image restoration process. MBSD assigns blur-level labels to image patches using a Patch Blur Annotator (PBA), guiding a Multi-Scale Blur Estimator (MSBE) to predict soft blur probabilities and generate routing weights. These weights control a Blur-Adaptive Expert Mixer (BAEM), which adaptively combines features based on local blur severity. The features are then passed to a text-to-image diffusion model via a cross-attention mechanism, enabling region-specific restoration. Extensive experiments on public benchmarks demonstrate that MBSD delivers superior perceptual quality while maintaining competitive PSNR and SSIM, consistently outperforming state-of-the-art methods.

A fundamental task in the realms of computer vision, Low-Rank Matrix Recovery (LRMR) focuses on the inherent low-rank structure precise recovery from incomplete data and/or corrupted measurements given that the rank is a known prior or accurately estimated. However, it remains challenging for existing rank estimation methods to accurately estimate the rank of an ill-conditioned matrix. Also, existing LRMR optimization methods are heavily dependent on the chosen parameters, and are therefore difficult to adapt to different situations. Addressing these issues, A novel LEarning-based low-rank matrix recovery with Rank Estimation (LERE) is proposed. More specifically, considering the characteristics of the Gerschgorin disk's center and radius, a new heuristic decision rule in the Gerschgorin Disk Theorem is significantly enhanced and the low-rank boundary can be exactly located, which leads to a marked improvement in the accuracy of rank estimation. According to the estimated rank, we select row and column sub-matrices from the observation matrix by uniformly random sampling. A 17-iteration feedforward-recurrent-mixed neural network is then adapted to learn the parameters in the sub-matrix recovery processing. Finally, by the correlation of the row sub-matrix and column sub-matrix, LERE successfully recovers the underlying low-rank matrix. Overall, LERE is more efficient and robust than existing LRMR methods. Experimental results demonstrate that LERE surpasses state-of-the-art (SOTA) methods. The code for this work is accessible at https://github.com/zhengqinxu/LERE.

Robust principal component analysis (RPCA) is widely studied in computer vision. Recently an adaptive rank estimate based RPCA has achieved top performance in low-level vision tasks without the prior rank, but both the rank estimate and RPCA optimization algorithm involve singular value decomposition, which requires extremely huge computational resource for large-scale matrices. To address these issues, an efficient RPCA (eRPCA) algorithm is proposed based on block Krylov iteration and CUR decomposition in this paper. Specifically, the Krylov iteration method is employed to approximate the eigenvalue decomposition in the rank estimation, which requires$O(ndrq+n(rq)^{2})$for an$(n\times d)$input matrix, in which$q$is a parameter with a small value,$r$is the target rank. Based on the estimated rank, CUR decomposition is adopted to replace SVD in updating low-rank matrix component, whose complexity reduces from$O(rnd)$to$O(r^{2}n)$per iteration. Experimental results verify the efficiency and effectiveness of the proposed eRPCA over the state-of-the-art methods in various low-level vision applications.

Robust principal component analysis (RPCA) and its variants have gained vide applications in computer vision. However, these methods either involve manual adjustment of some parameters, or require the rank of a low-rank matrix to be known a prior. In this paper, an adaptive rank estimate based RPCA (ARE-RPCA) is proposed, which adaptively assigns weights on different singular values via rank estimation. More specifically, we study the characteristics of the low-rank matrix, and develop an improved Gerschgorin disk theorem to estimate the rank of the low-rank matrix accurately. Furthermore in view of the issue occurred in the Gerschgorin disk theorem that adjustment factor need to be manually pre-defined, an adaptive setting method, which greatly facilitates the practical implementation of the rank estimation, is presented. Then, the weights of singular values in the nuclear norm are updated adaptively based on iteratively estimated rank, and the resultant low-rank matrix is close to the target. Experimental results show that the proposed ARE-RPCA outperforms the state-of-the-art methods in various complex scenarios.

Spatially varying exposures via rolling shutter is an efficient way to capture differently exposed images for high dynamic range (HDR) scenes. Neither camera movement nor moving objects is an issue for such a captured method. However, a possible issue is that the resolution of captured images is reduced. In this paper, we introduce a novel cross image cubic interpolator for the spatially varying exposures via the rolling shutter. Both intra correlation among pixels with the same exposure and inter correlation among pixels with the different exposures are utilized by the proposed interpolator. Experimental results show that quality of upsampled images is significantly improved.

This paper presents a new medical image segmentation method by using wavelet frame energy distribution, which is the sum of squares of the wavelet frame coefficients at each pixel. This work shows that the wavelet frame energy distribution contains the fine texture information extracted from images with low intensity contrast and complex structures using wavelet frame transform. Thus it is employed to enhance the segmentation quality under some challenge conditions such as low intensity contrast, weak/ambiguous boundaries, intensity inhomogeneity and heavy noise. Furthermore, this paper adopts convex relaxation approach to solve the corresponding optimization problem instead of classical level-set method, so the leading numerical computation is efficient and robust to initialization values. Experimental results also illustrate the efficiency of the proposed segmentation method for biomedical images under these extreme imaging conditions.

It is well known that modern CCD/CMOS digital cameras produce color images contaminated by mixed photon-electronic noise, which is a mixture of signal-dependent optical photon noise and signal-independent electronic noise. In statistical, variance of the mixed noise is a line function of mean intensity on the pixel. Based on this camera variance-mean model, we propose a fast and robust approach to generate a high quality image from a pair of noisy/blurred low-lighting images with moving objects along any directions. More precisely, camera noise variance model is employed to separate the effects of noise from moving objects on the images, followed by BM3D denoising method to reduce the noise of identified moving objects in the noisy image. Then motion blur in the blurred image is removed by a patching method, which is robust to object movements along any directions. We validate the effectiveness of our proposed approach on real images with moving objects in this paper.

In this paper, we propose an efficient algorithm for solving a balanced approach in frame-based image deblurring. The balanced approach is usually formulated as a minimization problem involving an ℓ2data-fidelity term, an ℓ1regularizer on sparsity of frame coefficients, and a penalty on distance of sparse frame coefficients to the canonical frame coefficients. The balanced approach bridges synthesis-based and analysis-based approaches. Our algorithm is based on a variable splitting strategy and the classical alternating direction method (ADM). This paper shows how the proposed algorithm can be applied to solve the balanced approach efficiently. More precisely, a regularized version of the Hessian matrix of the ℓ2data-fidelity term is involved, and by exploiting fast tight frame and circular structure of the observation matrix, the matrix can perform efficiently for image deblurring application. Convergence of the proposed algorithm is guaranteed by the existing ADM theory. Numerical simulations illustrate the efficiency of our proposed algorithm in frame-based image deblurring.

In a typical image synthesis where multiple differently exposed images are captured for processing, it is important to design an anti-ghost algorithm so as to prevent ghosting artifacts from appearing in the final image. An anti-ghost algorithm is usually composed of a detection module and a correction module. In this paper, a new detection module is proposed to detect non-consistent pixels of all input images without predefining any initial reference image. The proposed module is suitable when an interactive mode is desired. In addition, a bidirectional approach is introduced to correct the non-consistent pixels in the correction module. Compared with existing unidirectional correction methods, the proposed bidirectional correction approach uses information from two adjacent images of a detected image to correct its non-consistent pixels. This leads to a quality improvement in the final image.

This paper presents an efficient algorithm for solving a balanced regularization problem in the frame-based image restoration. The balanced regularization is usually formulated as a minimization problem, involving an l(2) data-fidelity term, an l(1) regularizer on sparsity of frame coefficients, and a penalty on distance of sparse frame coefficients to the range of the frame operator. In image restoration, the balanced regularization approach bridges the synthesis-based and analysis-based approaches, and balances the fidelity, sparsity, and smoothness of the solution. Our proposed algorithm for solving the balanced optimal problem is based on a variable splitting strategy and the classical alternating direction method. This paper shows that the proposed algorithm is fast and efficient in solving the standard image restoration with balanced regularization. More precisely, a regularized version of the Hessian matrix of the l(2) data-fidelity term is involved, and by exploiting the related fast tight Parseval frame and the special structures of the observation matrices, the regularized Hessian matrix can perform quite efficiently for the frame-based standard image restoration applications, such as circular deconvolution in image deblurring and missing samples in image inpainting. Numerical simulations illustrate the efficiency of our proposed algorithm in the frame-based image restoration with balanced regularization.

This study addresses the joint robust linear transceiver design problems for a downlink multi-user multiple-input multiple-output (MIMO) antenna system in the presence of imperfect channel state information (CSI). The uncertainty in the channel is characteried by a norm-bounded region, and two robust optimal design problems are considered. One is aimed at minimising the total transmitter power subject to users' mean square error (MSE) constraints in the presence of channel uncertainty, the other is to minimise the worst-case sum-mean square error (sum-MSE) under power constraints for all admissible uncertainties. For these two problems, the authors propose two iterative algorithms based on second-order cone programming (SOCP) formulations, which can be efficiently solved and have less computational complexity than their semi-definite programming (SDP) counterparts. Simulation results also illustrate that the proposed robust design approaches can significantly reduce the computational complexity while achieving almost the same performance as the robust SDP methods.

A robust scheme is proposed to generate an anti-ghosting high dynamic range (HDR) image from a set of low dynamic range (LDR) images with different exposure times. Three major contributions of this paper are 1) a bi-directional prediction method; 2) an adaptive threshold for the classification of pixels; 3) Bayes estimator based methods for the on-line updating of predicted values and the synthesis of pixels to fill in the regions of moving objects to preserve their dynamic ranges. The proposed scheme is suitable for both static and dynamic scenes.

In this paper, we propose an intensity mapping function (IMF) based scheme to detect moving objects in a set of low dynamic range (LDR) images with different known exposure times. The objective is to remove ghosting artifacts from the eventual high dynamic range (HDR) image. Our contributions include a bidirectional similarity detection method, an adaptive threshold for movement detection, and an IMF based method for the synthesis of pixels to fill in the regions of moving objects. Experimental results show that the proposed scheme outperforms existing schemes.

This paper presents a robust and fast algorithm for automatically generating high dynamic range (HDR) images in presence of camera movement and moving objects. This scheme comprises five modules: 1) image alignment, 2) estimation of camera response function (CRF) in dynamic scenes, 3) moving object detection, 4) progressive image correction, and 5) construction of HDR images. The key advantage of the algorithm is the ability to generate HDR images without ghost artifact. The proposed algorithm is fast as it is a one-shot solution without iterative computation and post-processing or even manual operation. Experimental results demonstrate that the proposed method outperforms the existing commercial products.

This paper presents an improved fast mode decision algorithm for coarse grain scalability (CGS). The modified fast mode decision algorithm extends previous work to provide better encoder complexity reduction with insignificant degradation in picture quality. The candidate mode set is adaptive to the quantization parameter difference between a layer and its "base layer". Furthermore, the proposed scheme fully utilizes the statistics of mode transition between a layer and its "base layer" when the quantization parameter difference between these two layers is small. Simulation results demonstrate that the proposed scheme provides up to 64% of time saving compared with the original SVC encoder.

In this paper, we present a Wyner-Ziv coding based on random projections for image compression with side information at the decoder. The proposed coder consists of random projections (RPs), nested scalar quantization (NSQ), and Slepian-Wolf coding (SWC). Most of natural images are compressible or sparse in the sense that they are well-approximated by a linear combination of a few coefficients taken from a known basis, e.g., FFT or Wavelet basis. Recent results show that it is surprisingly possible to reconstruct compressible signal to within very high accuracy from limited random projections by solving a simple convex optimization program. Nested quantization provides a practical scheme for lossy source coding with side information at the decoder to achieve further compression. SWC is lossless source coding with side information at the decoder. In this paper, ideal SWC is assumed, thus rates are conditional entropies of NSQ quantization indices. Recently theoretical analysis shows that for the quadratic Gaussian case and at high rate, NSQ with ideal SWC performs the same as conventional entropy-coded quantization with side information available at both the encoder and decoder. We note that the measurements of random projects for a natural large-size image can behave like Gaussian random variables because most of random measurement matrices behave like Gaussian ones if their sizes are large. Hence, by combining random projections with NSQ and SWC, the tradeoff between compression rate and distortion will be improved. Simulation results support the proposed joint codec design and demonstrate considerable performance of the proposed compression systems.

This letter investigates a transmitted signaling technique using orthogonal unified complex Hadamard transform (UCHT) spreading sequences and the coherent RAKE receiver in direct-sequence code-division multiple-access (DS-CDMA) downlinks to maintain the orthogonality between users and reduce the effect of multipath fading and interference from other users. A general multipath-fading channel model is assumed. System performance is evaluated by means of signal-to-interference-plus-noise ratio (SINR) at the RAKE receiver. It is shown that the SINR of the system employing UCHT complex sequences is independent of the phase offsets between different paths, while the SINR of the system using Walsh-Hadamard (WH) sequences is related to the squared cosine of path phase offsets. As a result, the bit-error ratio performance of the DS-CDMA downlink system employing UCHT complex sequences is better than that of the system with WH sequences at high SINRs

Quadriphase complex sequences based on unified complex Hadamard transform (UCHT) are orthogonal and easy to generate [6]. There are sixty-four sets in UCHT-based sequences. Some sets of UCHT sequences provide better auto-correlation properties than orthogonal walsh-Hadamard (WH) sequences. In this paper, UCHT-based sequences are applied as spreading sequences in an asynchronous MC-DS-CDMA system. The bit-error rate (BER) performance of the underlying system with complex spreading sequences is investigated and simulation results show that the asynchronous MC-DS-CDMA system spread by UCHT sequences outperforms that spread by WH sequences in frequency selective fading channel.

Performance of quaternary direct-sequence spread-spectrum multiple-access (DS-SSMA) systems with complex signature sequences and complex modulators and receivers in flat Rayleigh fading is investigated in this paper. Due to the availability of potentially large sets of complex sequences with good correlation characteristics, the interest of using complex spreading sequences in DS-SSMA has increased dramatically. The complex spreading sequences investigated in this paper include the recently introduced orthogonal unified complex Hadamard transform (UCHT) sequences. In this paper, complex processing in modulators and receivers is also employed in order to take advantage of the correlation properties of complex signature sequences. The average bit error rate (BER) for quaternary synchronous systems is obtained first, and then the BER for quaternary asynchronous systems is evaluated using characteristic function approach. Result based on Gaussian approximation method is also presented for asynchronous systems. The numerical examples illustrate that the systems based on UCHT spreading sequences perform generally better than the Gold sequences and the 4-phase family A-sequences.

The paper addresses the problem of channel estimation for DS-CDMA systems undergoing time-varying multipath fading channels. The multipath fading channels are modeled as AR models. Based on the minimum mean square error (MMSE) criterion, the linear optimal estimator is obtained by a spectral factorization and a Diophantine polynomial matrix equation. The uncertainty of the channel model is taken into consideration to improve the robustness of the estimator. Compared with the Kalman estimator, the proposed algorithm has O(K/sup 2/) computational complexity, where K is the number of users. The simulation results show that the proposed estimator provides good estimation performance and robustness for fast fading channels.

This paper focuses on decentralized H/sub /spl infin// filtering problem for interconnected linear systems. The problem we address is to find a decentralized filter where each local filter is based only on local available information on its own subsystem and the overall filtering error is totally asymptotically stable and the L/sub 2/-gain from the exogenous noise input to the filtering error less than a prespecified level. This paper shows that the decentralized H/sub /spl infin// filtering problem can be solved by using linear matrix inequality (LMI) techniques, which are numerically efficient due to recent advances in convex optimization.