Search Results (36)

Single-image depth from defocus is limited by blur-radius ambiguity: two object distances on different sides of the focal plane can produce similar point spread functions (PSFs). We study single-shot dual-focus imaging (DFI) with a polarizer-free liquid crystal (LC) lens, where the ordinary-ray component remains unmodulated while the extraordinary-ray component is refocused. Unlike conventional multi-capture DFD, the proposed system records a dual-focus superposition in one exposure and selects the optical setting before network training using the ambiguity-interval length A and PSF correlation $C_r$. We show that DFI does not reduce ambiguity unconditionally: its benefit depends on the LC-lens power. A deblurring-based depth estimation network with a physics-calibrated Wiener bank translates the selected dual-focus cue into quantitative depth. On model-matched synthetic DFI data with an 8 m focus setting, the proposed configuration reduces RMS error from $0.227\pm 0.001$ m to $0.190\pm 0.001$ m (mean ± s.d. over four independent runs) relative to single-focus imaging. A 116-pair indoor prototype dataset provides feasibility evidence under the tested configuration, but is not used to claim broad physical generalization. Full article

Traditional hardware-based approaches for depth-of-field extension (DOF-E), such as optimized lens design or focus-stacking via layer scanning, are often plagued by bulkiness and prohibitive costs. Meanwhile, conventional multi-focus image fusion algorithms demand precise spatial alignment, a challenge that becomes particularly acute in applications like microscopy. To address these limitations, this paper proposed a novel single-image DOF-E method termed SDENet. The method adopts an encoder –decoder architecture enhanced with multi-scale self-attention and depth enhancement modules, enabling the transformation of a single partially focused image into a fully focused output while effectively recovering regions outside the original depth of field (DOF). To support model training and performance evaluation, we introduce a dedicated dataset (MSED) containing 1772 pairs of single-focus and all-focus images covering diverse scenes. Experimental results on multiple datasets verify that SDENet significantly outperforms state-of-the-art deblurring methods, achieving a PSNR of 26.98 dB and SSIM of 0.846 on the DPDD dataset, which represents a substantial improvement in clarity and visual coherence compared to existing techniques. Furthermore, SDENet demonstrates competitive performance with multi-image fusion methods while requiring only a single input. Full article

Sparsity-driven regularization has undergone significant development in single-image restoration, particularly with the transition from handcrafted priors to trainable deep architectures. In this work, a geometric prior-enhanced deep image prior (DIP) framework, termed DIP-MC, is proposed that integrates mean curvature (MC) regularization to promote natural smoothness and structural coherence in reconstructed images. To strengthen the representational capacity of DIP, a self-attention module is incorporated between the encoder and decoder, enabling the network to capture long-range dependencies and preserve fine-scale textures. In contrast to total variation (TV), which frequently produces piecewise-constant artifacts and staircasing, MC regularization leverages curvature information, resulting in smoother transitions while maintaining sharp structural boundaries. DIP-MC is evaluated on standard grayscale and color image denoising and deblurring tasks using benchmark datasets including BSD68, Classic5, LIVE1, Set5, Set12, Set14, and the Levin dataset. Quantitative performance is assessed using peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) metrics. Experimental results demonstrate that DIP-MC consistently outperformed the DIP-TV baseline with 26.49 PSNR and 0.9 SSIM. It achieved competitive performance relative to BM3D and EPLL models with 28.6 PSNR and 0.87 SSIM while producing visually more natural reconstructions with improved detail fidelity. Furthermore, the learning dynamics of DIP-MC are analyzed by examining update-cost behavior during optimization, visualizing the best-performing network weights, and monitoring PSNR and SSIM progression across training epochs. These evaluations indicate that DIP-MC exhibits superior stability and convergence characteristics. Overall, DIP-MC establishes itself as a robust, scalable, and geometrically informed framework for high-quality single-image restoration. Full article

Recent advances in 3D Gaussian Splatting (3DGS) have achieved remarkable performance in scene reconstruction and novel view synthesis on benchmark datasets. However, real-world images are frequently affected by degradations such as camera shake, object motion, and lens defocus, which not only compromise image quality but also severely hinder the accuracy of 3D reconstruction—particularly in fine details. While existing deblurring approaches have made progress, most are limited to addressing a single type of blur, rendering them inadequate for complex scenarios involving multiple blur sources and resolution degradation. To address these challenges, we propose Gaussian Splatting with Multi-Scale Deblurring and Resolution Enhancement (GS-MSDR), a novel framework that seamlessly integrates multi-scale deblurring and resolution enhancement. At its core, our Multi-scale Adaptive Attention Network (MAAN) fuses multi-scale features to enhance image information, while the Multi-modal Context Adapter (MCA) and adaptive spatial pooling modules further refine feature representation, facilitating the recovery of fine details in degraded regions. Additionally, our Hierarchical Progressive Kernel Optimization (HPKO) method mitigates ambiguity and ensures precise detail reconstruction through layer-wise optimization. Extensive experiments demonstrate that GS-MSDR consistently outperforms state-of-the-art methods under diverse degraded scenarios, achieving superior deblurring, accurate 3D reconstruction, and efficient rendering within the 3DGS framework. Full article

In response to the inherent limitations of uncooled infrared imaging devices and the image degradation caused by UAV (Unmanned Aerial Vehicle) platform motion, resulting in low contrast and blurred details, a novel single-image blind deblurring and enhancement network is proposed for UAV infrared imagery. This network achieves global blind deblurring and local feature enhancement, laying a foundation for subsequent high-level vision tasks. The proposed architecture comprises three key modules: feature extraction, feature fusion, and simulated diffusion. Furthermore, a region-specific pixel loss is introduced to strengthen local feature perception, while a progressive training strategy is adopted to optimize model performance. Experimental results on public infrared datasets demonstrate that the presented method outperforms state-of-the-art methods HCTIRdeblur, reducing parameter count by 18.4%, improving PSNR by 10.7%, and decreasing edge inference time by 25.6%. This work addresses critical challenges in UAV infrared image processing and offers a promising solution for real-world applications. Full article

This work introduces a two-stage framework, named the Distorted underwater image Restoration Network (DR-Net), to address the complex degradation of underwater images caused by turbulence, water flow fluctuations, and optical properties of water. The first stage employs the Distortion Estimation Network (DE-Net), which leverages a fusion of Transformer and U-Net architectures to estimate distortion information from degraded images and focuses on image distortion recovery. Subsequently, the Image Restoration Generative Adversarial Network (IR-GAN) in the second stage utilizes this estimated distortion information to deblur images and regenerate lost details. Qualitative and quantitative evaluations on both synthetic and real-world image datasets demonstrate that DR-Net outperforms traditional methods and restoration strategies from different perspectives, showcasing its broader applicability and robustness. Our approach enables the restoration of underwater images from a single frame, which facilitates the acquisition of marine resources and enhances seabed exploration capabilities. Full article

In this study, we propose a dynamic scene deblurring approach using a deep supervised attention network. While existing deep learning-based deblurring methods have significantly outperformed traditional techniques, several challenges remain: (1) Invariant weights: Small conventional neural network (CNN) models struggle to address the spatially variant nature of dynamic scene deblurring, making it difficult to capture the necessary information. A more effective architecture is needed to better extract valuable features. (2) Limitations of standard datasets: Current datasets often suffer from low data volume, unclear ground truth (GT) images, and a single blur scale, which hinders performance. To address these challenges, we propose a multi-scale, end-to-end recurrent network that utilizes supervised attention to recover sharp images. The supervised attention mechanism focuses the model on features most relevant to ambiguous information as data are passed between networks at difference scales. Additionally, we introduce new loss functions to overcome the limitations of the peak signal-to-noise ratio (PSNR) estimation metric. By incorporating a fast Fourier transform (FFT), our method maps features into frequency space, aiding in the recovery of lost high-frequency details. Experimental results demonstrate that our model outperforms previous methods in both quantitative and qualitative evaluations, producing higher-quality deblurring results. Full article

Deploying high-performance image restoration models on drones is critical for applications like autonomous navigation, surveillance, and environmental monitoring. However, the computational and memory limitations of drones pose significant challenges to utilizing complex image restoration models in real-world scenarios. To address this issue, we propose the Simultaneous Learning Knowledge Distillation (SLKD) framework, specifically designed to compress image restoration models for resource-constrained drones. SLKD introduces a dual-teacher, single-student architecture that integrates two complementary learning strategies: Degradation Removal Learning (DRL) and Image Reconstruction Learning (IRL). In DRL, the student encoder learns to eliminate degradation factors by mimicking Teacher A, which processes degraded images utilizing a BRISQUE-based extractor to capture degradation-sensitive natural scene statistics. Concurrently, in IRL, the student decoder reconstructs clean images by learning from Teacher B, which processes clean images, guided by a PIQE-based extractor that emphasizes the preservation of edge and texture features essential for high-quality reconstruction. This dual-teacher approach enables the student model to learn from both degraded and clean images simultaneously, achieving robust image restoration while significantly reducing computational complexity. Experimental evaluations across five benchmark datasets and three restoration tasks—deraining, deblurring, and dehazing—demonstrate that, compared to the teacher models, the SLKD student models achieve an average reduction of 85.4% in FLOPs and 85.8% in model parameters, with only a slight average decrease of 2.6% in PSNR and 0.9% in SSIM. These results highlight the practicality of integrating SLKD-compressed models into autonomous systems, offering efficient and real-time image restoration for aerial platforms operating in challenging environments. Full article

Accurate and efficient measurement of deposited droplets’ volume is vital to achieve zero-defect manufacturing in inkjet printed organic light-emitting diode (OLED), but it remains a challenge due to droplets’ featurelessness. In our work, coherence scanning interferometry (CSI) is utilized to measure the volume. However, the CSI redundant sampling and image degradation led by the sample’s transparency decrease the efficiency and accuracy. Based on the prior degradation and strong representation for context, a novel method, volume measurement via fringe distribution module (VMFD), is proposed to directly measure the volume by single interferogram without redundant sampling. Firstly, the 3D point spread function (PSF) for CSI imaging is modeling to relate the degradation and image. Secondly, the Zernike to PSF (ZTP) module is proposed to efficiently compute the aberrations to PSF. Then, a physics aberration restoration network (PARN) is designed to remove the degradation via the channel Transformer and U-net architecture. The long term context is learned by PARN and beneficial to restoration. The restored fringes are used to measure the droplet’s volume by constrained regression network (CRN) module. Finally, the performances on public datasets and the volume measurement experiments show the promising deblurring, measurement precision and efficiency. Full article

Multispectral remote sensing images contain abundant information about the distribution and reflectance of ground objects, playing a crucial role in target detection, environmental monitoring, and resource exploration. However, due to the complexity of the imaging process in multispectral remote sensing, image blur is inevitable, and the blur kernel is typically unknown. In recent years, many researchers have focused on blind image deblurring, but most of these methods are based on single-band images. When applied to CASEarth satellite multispectral images, the spectral correlation is unutilized. To address this limitation, this paper proposes a novel approach that leverages the characteristics of multispectral data more effectively. We introduce an inter-band gradient similarity prior and incorporate it into the patch-wise minimal pixel (PMP)-based deblurring model. This approach aims to utilize the spectral correlation across bands to improve deblurring performance. A solution algorithm is established by combining the half-quadratic splitting method with alternating minimization. Subjectively, the final experiments on CASEarth multispectral images demonstrate that the proposed method offers good visual effects while enhancing edge sharpness. Objectively, our method leads to an average improvement in point sharpness by a factor of 1.6, an increase in edge strength level by a factor of 1.17, and an enhancement in RMS contrast by a factor of 1.11. Full article

Recent studies have proposed methods for extracting latent sharp frames from a single blurred image. However, these methods still suffer from limitations in restoring satisfactory images. In addition, most existing methods are limited to decomposing a blurred image into sharp frames with a fixed frame rate. To address these problems, we present an Arbitrary Time Blur Decomposition Triple Generative Adversarial Network (ABDGAN) that restores sharp frames with flexible frame rates. Our framework plays a min–max game consisting of a generator, a discriminator, and a time-code predictor. The generator serves as a time-conditional deblurring network, while the discriminator and the label predictor provide feedback to the generator on producing realistic and sharp image depending on given time code. To provide adequate feedback for the generator, we propose a critic-guided (CG) loss by collaboration of the discriminator and time-code predictor. We also propose a pairwise order-consistency (POC) loss to ensure that each pixel in a predicted image consistently corresponds to the same ground-truth frame. Extensive experiments show that our method outperforms previously reported methods in both qualitative and quantitative evaluations. Compared to the best competitor, the proposed ABDGAN improves PSNR, SSIM, and LPIPS on the GoPro test set by $16.67\%$, $9.16\%$, and $36.61\%$, respectively. For the B-Aist++ test set, our method shows improvements of $6.99\%$, $2.38\%$, and $17.05\%$ in PSNR, SSIM, and LPIPS, respectively, compared to the best competitive method. Full article

In recent years, with the rapid developments in deep learning and graphics processing units, learning-based defocus deblurring has made favorable achievements. However, the current methods are not effective in processing blurred images with a large depth of field. The greater the depth of field, the blurrier the image, namely, the image contains large blurry regions and encounters severe blur. The fundamental reason for the unsatisfactory results is that it is difficult to extract effective features from the blurred images with large blurry regions. For this reason, a new FFEM (Fuzzy Feature Extraction Module) is proposed to enhance the encoder’s ability to extract features from images with large blurry regions. After using the FFEM during encoding, its PSNR (Peak Signal-to-Noise Ratio) is improved by 1.33% on the DPDD (Dual-Pixel Defocus Deblurring). Moreover, images with large blurry regions often cause the current algorithms to generate artifacts in their results. Therefore, a new module named ARM (Artifact Removal Module) is proposed in this work and employed during decoding. After utilizing the ARM during decoding, its PSNR is improved by 2.49% on the DPDD. After using the FFEM and the ARM simultaneously, compared to the latest algorithms, the PSNR of our method is improved by 3.29% on the DPDD. Following the previous research in this field, qualitative and quantitative experiments are conducted on the DPDD and the RealDOF (Real Depth of Field), and the experimental results indicate that our method surpasses the state-of-the-art algorithms in three objective metrics. Full article

Recent studies in transillumination imaging for developing an optical computed tomography device for small animal and human body parts have used deep learning networks to suppress the scattering effect, estimate depth information of light-absorbing structures, and reconstruct three-dimensional images of de-blurred structures. However, they still have limitations, such as knowing the information of the structure in advance, only processing simple structures, limited effectiveness for structures with a depth of about 15 mm, and the need to use separated deep learning networks for de-blurring and estimating information. Furthermore, the current technique cannot handle multiple structures distributed at different depths next to each other in the same image. To overcome the mentioned limitations in transillumination imaging, this study proposed a pixel-by-pixel scanning technique in combination with deep learning networks (Attention Res-UNet for scattering suppression and DenseNet-169 for depth estimation) to estimate the existence of each pixel and the relative structural depth information. The efficacy of the proposed method was evaluated through experiments that involved a complex model within a tissue-equivalent phantom and a mouse, achieving a reconstruction error of $2.18$% compared to the dimensions of the ground truth when using the fully convolutional network. Furthermore, we could use the depth matrix obtained from the convolutional neural network (DenseNet-169) to reconstruct the absorbing structures using a binary thresholding method, which produced a reconstruction error of $6.82$%. Therefore, only one convolutional neural network (DenseNet-169) must be used for depth estimation and explicit image reconstruction. Therefore, it reduces time and computational resources. With depth information at each pixel, reconstruction of 3D image of the de-blurred structures could be performed even from a single blurred image. These results confirm the feasibility and robustness of the proposed pixel-by-pixel scanning technique to restore the internal structure of the body, including intricate networks such as blood vessels or abnormal tissues. Full article

Image blur, often caused by camera shake and object movement, poses a significant challenge in computer vision. Image deblurring strives to restore clarity to these images. Traditional single-stage methods, while effective in detail enhancement, often neglect global context in favor of local information. Yet, both aspects are crucial, especially in real-life scenarios where images are typically large and subject to various blurs. Addressing this, we introduce CNB Net, an innovative deblurring network adept at integrating global and local insights for enhanced image restoration. The network operates in two stages, utilizing our specially designed Convolution and Normalization-Based Block (CNB Block) and Convolution and Normalization-Based Plus Block (CNBP Block) for multi-scale information extraction. A progressive learning approach is adopted with a Feature Active Selection (FAS) module at the end of each stage that captures spatial detail information under the guidance of real images. The Two-Stage Feature Fusion (TSFF) module reduces information loss caused by downsampling operations while enriching features across stages for increased robustness. We conduct experiments on the GoPro dataset and the HIDE dataset. On the GoPro dataset, our Peak Signal-to-Noise Ratio (PSNR) result is 32.21 and the Structural Similarity (SSIM) result is 0.950; and on the HIDE dataset, our PSNR result is 30.38 and the SSIM result is 0.932. Our results exceed other similar algorithms. By comparing the generated feature maps, we find that our model takes into account both global and local information well. Full article

Convolutional neural networks (CNNs) have become instrumental in advancing multi-frame image super-resolution (SR), a technique that merges multiple low-resolution images of the same scene into a high-resolution image. In this paper, a novel deep learning multi-frame SR algorithm is introduced. The proposed CNN model, named Exponential Fusion of Interpolated Frames Network (EFIF-Net), seamlessly integrates fusion and restoration within an end-to-end network. Key features of the new EFIF-Net include a custom exponentially weighted fusion (EWF) layer for image fusion and a modification of the Residual Channel Attention Network for restoration to deblur the fused image. Input frames are registered with subpixel accuracy using an affine motion model to capture the camera platform motion. The frames are externally upsampled using single-image interpolation. The interpolated frames are then fused with the custom EWF layer, employing subpixel registration information to give more weight to pixels with less interpolation error. Realistic image acquisition conditions are simulated to generate training and testing datasets with corresponding ground truths. The observation model captures optical degradation from diffraction and detector integration from the sensor. The experimental results demonstrate the efficacy of EFIF-Net using both simulated and real camera data. The real camera results use authentic, unaltered camera data without artificial downsampling or degradation. Full article