Image Quality Degradation Research Articles

Efficient Distortion-Free Neural Projector Deblurring in Dynamic Projection Mapping.

Dynamic Projection Mapping (DPM) necessitates geometric compensation of the projection image based on the position and orientation of moving objects. Additionally, the projector's shallow depth of field results in pronounced defocus blur even with minimal object movement. Achieving delay-free DPM with high image quality requires real-time implementation of geometric compensation and projector deblurring. To meet this demand, we propose a framework comprising two neural components: one for geometric compensation and another for projector deblurring. The former component warps the image by detecting the optical flow of each pixel in both the projection and captured images. The latter component performs real-time sharpening as needed. Ideally, our network's parameters should be trained on data acquired in an actual environment. However, training the network from scratch while executing DPM, which demands real-time image generation, is impractical. Therefore, the network must undergo pre-training. Unfortunately, there are no publicly available large real datasets for DPM due to the diverse image quality degradation patterns. To address this challenge, we propose a realistic synthetic data generation method that numerically models geometric distortion and defocus blur in real-world DPM. Through exhaustive experiments, we have confirmed that the model trained on the proposed dataset achieves projector deblurring in the presence of geometric distortions with a quality comparable to state-of-the-art methods.

Dark-field super-oscillatory microscopy with high-pass super-oscillatory filters

Super-resolution imaging of transparent objects is particularly challenging due to the interference caused by background light. This interference can significantly degrade image quality by reducing contrast and obscuring fine details. In this work, high-pass super-oscillatory masks are designed to address this issue by filtering out the background light on the Fourier plane. The resolution of the corresponding super-oscillatory point-spread function is 0.66 times the diffraction limit, enabling the resolution of transparent objects with 67% transparency at sub-wavelength scales. Additionally, the high-pass super-oscillatory masks are designed for a 1080 × 1920 liquid-crystal spatial light modulator, making future experimental implementation straightforward. This facilitates easy switching between bright-field and dark-field super-oscillatory microscopy, broadening the range of application scenarios for the system.

Robot Localization Method Based on Multi-Sensor Fusion in Low-Light Environment

When robots perform localization in indoor low-light environments, factors such as weak and uneven lighting can degrade image quality. This degradation results in a reduced number of feature extractions by the visual odometry front end and may even cause tracking loss, thereby impacting the algorithm’s positioning accuracy. To enhance the localization accuracy of mobile robots in indoor low-light environments, this paper proposes a visual inertial odometry method (L-MSCKF) based on the multi-state constraint Kalman filter. Addressing the challenges of low-light conditions, we integrated Inertial Measurement Unit (IMU) data with stereo vision odometry. The algorithm includes an image enhancement module and a gyroscope zero-bias correction mechanism to facilitate feature matching in stereo vision odometry. We conducted tests on the EuRoC dataset and compared our method with other similar algorithms, thereby validating the effectiveness and accuracy of L-MSCKF.

Instance Segmentation XXL-CT Challenge of a Historic Airplane

Instance segmentation of compound objects in XXL-CT imagery poses a unique challenge in non-destructive testing. This complexity arises from the lack of known reference segmentation labels, limited applicable segmentation tools, as well as partially degraded image quality. To asses recent advancements in the field of machine learning-based image segmentation, the ‘Instance Segmentation XXL-CT Challenge of a Historic Airplane’ was conducted. The challenge aimed to explore automatic or interactive instance segmentation methods for an efficient delineation of the different aircraft components, such as screws, rivets, metal sheets or pressure tubes. We report the organization and outcome of this challenge and describe the capabilities and limitations of the submitted segmentation methods.

Polarization-insensitive optical coherence tomography using pseudo-depolarized reference light for mitigating birefringence-related image artifacts.

Optical coherence tomography (OCT) images are prone to image artifacts due to the birefringence of the sample or the optical system when a polarized light source is used for imaging. These artifacts can lead to degraded image quality and diagnostic information. We aim to mitigate these birefringence-related artifacts in OCT images by adding a depolarizer module in the reference arm of the interferometer. We investigated different configurations of liquid crystal patterned retarders as pseudo-depolarizers in the reference arm of OCT setups. We identified the most effective depolarization module layout for polarization artifact suppression for a spectral-domain OCT system based on a Michelson and a Mach-Zehnder interferometer. The performance of our approach was demonstrated in an achromatic quarter-wave plate allowing the selection of a variety of sample polarization states. A substantial improvement of the OCT signal magnitude was observed after placing the optimal depolarizer configuration, reducing the cross-polarization artifact from 5.7 to 1.8dB and from 8.0 to 1.0dB below the co-polarized signal for the fiber-based Michelson and Mach-Zehnder setup, respectively. An imaging experiment in the birefringent scleral tissue of a post-mortem alpine marmot eye and a mouse tail specimen further showcased a significant improvement in the detected signal intensity and an enhanced OCT image quality followed by a drastic elimination of the birefringence-related artifacts. Our study presents a simple yet cost-effective technique to mitigate birefringence-related artifacts in OCT imaging. This method can be readily implemented in existing OCT technology and improve the effectiveness of various OCT imaging applications in biomedicine.

Parametric Analytical Modulation Transfer Function Model in Turbid Atmosphere with Application to Image Restoration

To address the issues of image blurring and color distortion in hazy conditions, an image restoration method based on a parametric analytical modulation transfer function model is proposed under turbid atmospheric conditions. A source database is established using a numerical radiative transfer method based on discrete ordinate. Through multivariate nonlinear fitting and linear interpolation, the quantitative relationships among critical spatial frequency, turbid atmospheric MTF, and key atmospheric optical parameters—such as optical thickness, single scattering albedo, and asymmetry factor—are examined. A fast and efficient parametric analytical MTF model for turbid atmospheres is developed and applied to restore images affected by fog. The results demonstrate that, within the applicable range of the model, the model’s maximum mean relative error and the root mean square error are 7.16% and 0.0454, respectively. The computational speed is nearly a thousand times faster than that of the numerical radiative transfer method, achieving high accuracy and ease of application. Images restored using this model exhibit enhanced clarity and quality, effectively compensating for the degradation in image quality caused by turbid atmospheres. This approach represents a novel solution to the challenges of image processing in complex atmospheric environments.

Image shadow removal based on pseudo-illuminated region and log domain transformation

ABSTRACT The presence of shadows in images can significantly degrade image quality. To address the challenges, this study utilizes pseudo-illumination regions and logarithmic domain transformations. Firstly, the input shadow image and its corresponding shadow region are segmented and clustered into multiple image blocks. Then, a comprehensive consideration of distance, color, and texture features is employed to construct pseudo illumination regions. Subsequently, the designed logarithmic domain transformation function is utilized for shadow removal. Finally, color correction and optimization of shadow edges complete the overall process. The feasibility of this approach has been preliminarily verified through experimental analysis.

A fusion framework with multi-scale convolution and triple-branch cascaded transformer for underwater image enhancement

Acquiring high-quality underwater images is critical for various marine applications. However, light absorption and scattering problems in underwater environments severely degrade image quality. To address these issues, this study proposes a Fusion Framework with Multi-Scale Convolution and Triple-Branch Cascaded Transformer for Underwater Image Enhancement(FMTformer). This innovative framework incorporates multi-scale convolution and three-branch cascade transformer to enhance underwater images effectively. The FMTformer framework adds in the Multi-Conv Multi-Scale Fusion (MCMF) mechanism, which utilizes a spectrum of convolutional kernels to adeptly extract multi-scale features from both the base and detail layers of the decomposed image. This method ensures the capture of both high- and low-frequency information. Furthermore, this research introduces the Tri-Branch Self-Attention Transformer (TBSAT), designed to get cross-dimensional interactions via its Tri-Branch structure, significantly refines image processing quality. The framework also embedded the Value Reconstruct Cascade Transformer (VRCT), which refines feature map representation through mixed convolution, yielding enriched attention maps. Empirical evidence indicates that FMTformer achieves parity with the state-of-the-art in both subjective and objective evaluation metrics, outperforming extant methodologies.

Stable successive Neural Image Compression via coherent demodulation-based transformation

Neural Image Compression (NIC) has made significant strides in recent years. However, the existing NIC methods demonstrate instability issues during iterative re-compression cycles, which can degrade image quality with each cycle. This paper introduces a novel framework aimed at enhancing the stability of NIC methods. We first conducted a theoretical analysis and identified that the instability in current NIC methods stems from a lack of idempotency in transformations. Drawing from the domain of signal processing, we then examined the principles of idempotency in coherent demodulation techniques. This examination led to the identification of three foundational principles that inform the design of stable transformations: the cosine function, parameter sharing, and low-pass filtering. Leveraging these insights, we propose the innovative Coherent Demodulation-based Transformation (CDT), which is designed to address the stability challenges in NIC by incorporating these principles into its architecture. The experimental results suggest that CDT not only significantly improve the re-compression stability but also preserves the codec’s rate–distortion performance. Furthermore, it can be broadly applied in current NIC structures. The effectiveness of the module endorses the viability of designing transformation networks based on Coherent Demodulation principles, playing a crucial role in enhancing stability of NIC. The code will be available at https://github.com/baoyu2020/Stable_SuccessiveNIC.

Computed tomography of the equine caudal spine and pelvis: Technique, image quality and anatomical variation in 56 clinical cases (2018-2023).

Cross-sectional imaging improves the diagnostic accuracy of complex anatomical regions. Computed tomography (CT) of the pelvis and caudal spine in a large group of live horses and ponies has not been previously reported. To describe the procedure for acquiring CT images of horses' caudal spine/pelvis under general anaesthesia (GA) and to detail the image quality, artefacts and anatomical variations in this region. Retrospective case series. Horses with CT of the caudal spine/pelvis were included. Horses under 6 months and CT examination performed post-mortem were excluded. Protocols, image quality, region of interest, anatomical features and morbidities were analysed. Fifty-six horses (8 months to 20 years, 85-680 kg) met the inclusion criteria. GA ranged from 10 to 60 min (mean: 30, median: 32). There were no adverse events recorded in any of the horses associated with the procedure. Images of all horses were considered of diagnostic quality. Anatomical variations were common and included the location of diverging (widest) interspinous space, the presence of spina bifida in the lumbar and sacral spine, the shape of the last lumbar vertebra and the location of intertransverse joints in terms of where they were present and the degree of fusion/modelling. Not all horses underwent CT examination of the same regions, the upper size limit of horses is unknown and will vary depending on bore size and table infrastructure. Image noise, particularly in large horses and beam hardening artefacts from hardware and pelvis degraded image quality. Images were of insufficient quality in large horses for soft tissue interpretation. CT of the caudal spine and pelvis in live horses with wide-bore CT machines and modified patient infrastructure was safe and produced diagnostic images.

Efficient pure qP-wave modeling and reverse time migration in tilted transversely isotropic media calculated by a finite-difference approach

Subsurface anisotropy is commonly induced by shale layers, aligned cracks, and fine bedding and has a significant impact on seismic wave propagation. Ignoring anisotropic effects during seismic migration degrades image quality. Therefore, we derive a pure qP-wave equation with high accuracy for modeling seismic wave propagation in tilted transversely isotropic (TTI) media. However, the derived pure qP-wave equation requires a computationally expensive spectral-based method for performing numerical simulations. This is unsuitable for large-scale industrial applications, particularly 3D applications. For numerical efficiency, we first decompose the newly derived wave equation into some fractional differential operators and spatial derivatives. The spatial derivatives can be directly solved by conventional finite-difference (FD) approaches. Then, we use an asymptotic approximation to find an equivalent form of fractional differential operators, obtaining scalar operators that we can discretize with the FD method. Numerical tests show that our TTI pure qP-wave equation with an FD discretization can produce accurate and highly efficient wavefield simulations in TTI media. We also use our TTI pure qP-wave equation with an FD discretization as a forward engine to implement TTI reverse time migration (RTM). Synthetic examples and a field data test demonstrate that our TTI RTM can effectively correct the anisotropic effects, providing high-quality imaging results while maintaining good computational efficiency.

An illumination-guided dual-domain network for image exposure correction

Exposure problems, including underexposure and overexposure, can significantly degrade image quality. Poorly exposed images often suffer from coupled illumination degradation and detail degradation, aggravating the difficulty of recovery. These necessitate a spatial discriminating exposure correction, making achieving uniformly exposed and visually consistent images challenging. To address these issues, we propose an Illumination-guided Dual-domain Network (IDNet), which employs a Dual-Domain Module (DDM) to simultaneously recover illumination and details from the frequency and spatial domains, respectively. The DDM also integrates a structural re-parameterization technique to enhance the detail-aware capabilities with reduced computational cost. An Illumination Mask Predictor (IMP) is introduced to guide exposure correction by estimating the optimal illumination mask. The comparison with 26 methods on three benchmark datasets shows that IDNet achieves superior performance with fewer parameters and lower computational complexity. These results confirm the effectiveness and efficiency of our approach in enhancing image quality across various exposure scenarios.

Enhancing brain image quality with 3D U-net for stripe removal in light sheet fluorescence microscopy

Light Sheet Fluorescence Microscopy (LSFM) is increasingly popular in neuroimaging for its ability to capture high-resolution 3D neural data. However, the presence of stripe noise significantly degrades image quality, particularly in complex 3D stripes with varying widths and brightness, posing challenges in neuroscience research. Existing stripe removal algorithms excel in suppressing noise and preserving details in 2D images with simple stripes but struggle with the complexity of 3D stripes. To address this, we propose a novel 3D U-net model for Stripe Removal in Light sheet fluorescence microscopy (USRL). This approach directly learns and removes stripes in 3D space across different scales, employing a dual-resolution strategy to effectively handle stripes of varying complexities. Additionally, we integrate a nonlinear mapping technique to normalize high dynamic range and unevenly distributed data before applying the stripe removal algorithm. We validate our method on diverse datasets, demonstrating substantial improvements in peak signal-to-noise ratio (PSNR) compared to existing algorithms. Moreover, our algorithm exhibits robust performance when applied to real LSFM data. Through extensive validation experiments, both on test sets and real-world data, our approach outperforms traditional methods, affirming its effectiveness in enhancing image quality. Furthermore, the adaptability of our algorithm extends beyond LSFM applications to encompass other imaging modalities. This versatility underscores its potential to enhance image usability across various research disciplines.

Retina-Inspired Lightweight Spiking Convolutional Neural Network for Single-Image Dehazing.

Suspended particles in hazy medium absorb and scatter light, severely degrading imaging quality. Numerous single-image dehazing methods have been proposed to reconstruct clear images from hazy ones. However, most of them focus on increasing depth and width to improve dehazing performance, which incurs high computation and energy costs. To address this issue, we propose a lightweight spiking convolutional neural network (CNN) referred to as retina-inspired spiking CNN (RI-SCNN) for the reconstruction of hazy images. Unlike conventional dehazing techniques, first, our proposed network simulates the hierarchical structure and cellular function of the retina and devises five network modules to efficiently encode and extract image features through ON and OFF roads. Furthermore, the linear reconstruction mechanism is introduced to integrate the outputs from different roads, adaptively preserving regions with optimal details and constructing a comprehensive visual representation. Finally, by the transformed atmospheric scattering formula, our network can generate the dehazy image. Incorporating the microscale spiking mechanism of the brain, the entire network leverages discrete binary spike trains for information encoding and transmission, directly trained by spiking surrogate gradient learning on integrate-and-fire (IF) neurons. Experimental results demonstrate the superiority of the proposed RI-SCNN in terms of quantitative dehazing performance, qualitative visual effect, energy efficiency, and run speed. Considering its lightweight architecture with ultralow computation and energy costs, the network is encouraged to be deployed in the visual sensor hardware to improve overall performance.

A HRWS SAR Motion Compensation Method with Multichannel Phase Correction

The multichannel synthetic aperture radar (SAR) possesses the capability to acquire high-resolution, wide-swath SAR imagery, which has great potential for application. However, similar to traditional single-channel SAR systems, it suffers from imaging quality degradation due to motion errors. Many motion compensation algorithms have been used to improve the quality of single-channel SAR images, while fewer studies have been conducted on multichannel SAR motion compensation methods. The sub-image motion compensation method utilizes the single channel motion errors to perform multichannel motion errors compensation, considering that multiple channels have the same phase errors. To improve the quality of multichannel SAR imaging when multiple channel motion errors are inconsistent, this paper proposes a motion compensation method with multichannel phase correction for HRWS SAR. First, the method derives the phase errors estimation model via maximum sharpness to simultaneously estimate multichannel phase. Then, it compensates for the motion errors of all channels during backprojection imaging. The inconsistent motion errors of multiple channels can be compensated by estimating the phase errors of all channels, improving the image quality. The channel phase errors can be corrected while compensating for the motion errors. Moreover, the experimental results of point targets and complex scenes validate the effectiveness of the proposed method.

Sterilization of image steganography using self-supervised convolutional neural network

Background With the development of steganography technology, lawbreakers can implement covert communication in social networks more easily, exacerbating network security risks. Sterilization of image steganography methods can eliminate secret messages to block the transmission of illegal covert communication. However, existing methods overly rely on cover-stego image pairs and are unable to sanitize unknown image, which reduces stego image blocking rate in social networks. Methods To address the above problems, this paper proposes an effective sterilization of image steganography method using self-supervised convolutional neural network (SS-Net), which does not require any prior knowledge of image steganography schemes. SS-Net includes a purification module and a refinement module. Firstly, the pixel-shuffle down-sampling in purification module is adopted to reduce the spatial correlation of pixels in the stgeo image, and improve the learning mode from supervised learning to self-supervised learning. Secondly, centrally masked convolutions and dilated convolution residual blocks are merged to eliminate secret messages and avoid image quality degradation. Finally, a refinement module is employed to improve image texture details and boundaries. Results A series of experiments show that SS-Net from BOSSbase test sets is able to balance the destruction of secret messages with image quality, achieving 100% blocking rate of stego image. Meanwhile, our method outperforms the state-of-the-art methods in secret messages elimination ability and image quality preserving ability.

Lazy Resampling: Fast and information preserving preprocessing for deep learning

Background and Objective:Preprocessing of data is a vital step for almost all deep learning workflows. In computer vision, manipulation of data intensity and spatial properties can improve network stability and can provide an important source of generalisation for deep neural networks. Models are frequently trained with preprocessing pipelines composed of many stages, but these pipelines come with a drawback; each stage that resamples the data costs time, degrades image quality, and adds bias to the output. Long pipelines can also be complex to design, especially in medical imaging, where cropping data early can cause significant artifacts. Methods:We present Lazy Resampling, a software that rephrases spatial preprocessing operations as a graphics pipeline. Rather than each transform individually modifying the data, the transforms generate transform descriptions that are composited together into a single resample operation wherever possible. This reduces pipeline execution time and, most importantly, limits signal degradation. It enables simpler pipeline design as crops and other operations become non-destructive. Lazy Resampling is designed in such a way that it provides the maximum benefit to users without requiring them to understand the underlying concepts or change the way that they build pipelines. Results:We evaluate Lazy Resampling by comparing traditional pipelines and the corresponding lazy resampling pipeline for the following tasks on Medical Segmentation Decathlon datasets. We demonstrate lower information loss in lazy pipelines vs. traditional pipelines. We demonstrate that Lazy Resampling can avoid catastrophic loss of semantic segmentation label accuracy occurring in traditional pipelines when passing labels through a pipeline and then back through the inverted pipeline. Finally, we demonstrate statistically significant improvements when training UNets for semantic segmentation. Conclusion:Lazy Resampling reduces the loss of information that occurs when running processing pipelines that traditionally have multiple resampling steps and enables researchers to build simpler pipelines by making operations such as rotation and cropping effectively non-destructive. It makes it possible to invert labels back through a pipeline without catastrophic loss of accuracy.A reference implementation for Lazy Resampling can be found at https://github.com/KCL-BMEIS/LazyResampling. Lazy Resampling is being implemented as a core feature in MONAI, an open source python-based deep learning library for medical imaging, with a roadmap for a full integration.

Blind deblurring of astronomical images using a SCGTV-based single-frame method

Atmospheric turbulence often distorts space target imaging, leading to degraded image quality. To address the issue of image quality degradation, various hardware and software approaches have been proposed, including adaptive optics, lucky imaging, and blind deconvolution. Traditional astronomical image deblurring algorithms rely on information from multiple frames, requiring extensive processing time and computational resources. This study introduces the saturation-corrected graph total variation (SCGTV) method to address low signal-to-noise ratio and pixel saturation in single-frame astronomical image deblurring. This method effectively minimizes the influence of atmospheric turbulence and noise by leveraging a reweighted graph total variation prior. Saturation correction and dark channel information are integrated in SCGTV to enhance resolution and reduce artifacts. The SCGTV method is well-designed for astronomical scenarios, successfully deblurring real-world astronomical images and demonstrating superior performance on thirty simulated dataset compared to other algorithms. Quantitative evaluations on artificially blurred datasets demonstrate that SCGTV outperforms existing methods. These enhancements provide significant benefits for astronomical observation and analysis.

Device-Less Data-Driven Cardiac and Respiratory Gating Using LAFOV PET Histo Images.

Background: The outstanding capabilities of modern Positron Emission Tomography (PET) to highlight small tumor lesions and provide pathological function assessment are at peril from image quality degradation caused by respiratory and cardiac motion. However, the advent of the long axial field-of-view (LAFOV) scanners with increased sensitivity, alongside the precise time-of-flight (TOF) of modern PET systems, enables the acquisition of ultrafast time resolution images, which can be used for estimating and correcting the cyclic motion. Methods: 0.25 s so-called [18F]FDG PET histo image series were generated in the scope of for detecting respiratory and cardiac frequency estimates applicable for performing device-less data-driven gated image reconstructions. The frequencies of the cardiac and respiratory motion were estimated for 18 patients using Short Time Fourier Transform (STFT) with 20 s and 30 s window segments, respectively. Results: The Fourier analysis provided time points usable as input to the gated reconstruction based on eight equally spaced time gates. The cardiac investigations showed estimates in accordance with the measured pulse oximeter references (p = 0.97) and a mean absolute difference of 0.4 ± 0.3 beats per minute (bpm). The respiratory frequencies were within the expected range of 10-20 respirations per minute (rpm) in 16 out of 18 patients. Using this setup, the analysis of three patients with visible lung tumors showed an increase in tumor SUVmax and a decrease in tumor volume compared to the non-gated reconstructed image. Conclusions: The method can provide signals that were applicable for gated reconstruction of both cardiac and respiratory motion, providing a potential increased diagnostic accuracy.

Noise-imitation learning: unpaired speckle noise reduction for optical coherence tomography

Objective.Optical coherence tomography (OCT) is widely used in clinical practice for its non-invasive, high-resolution imaging capabilities. However, speckle noise inherent to its low coherence principle can degrade image quality and compromise diagnostic accuracy. While deep learning methods have shown promise in reducing speckle noise, obtaining well-registered image pairs remains challenging, leading to the development of unpaired methods. Despite their potential, existing unpaired methods suffer from redundancy in network structures or interaction mechanisms. Therefore, a more streamlined method for unpaired OCT denoising is essential.Approach.In this work, we propose a novel unpaired method for OCT image denoising, referred to as noise-imitation learning (NIL). NIL comprises three primary modules: the noise extraction module, which extracts noise features by denoising noisy images; the noise imitation module, which synthesizes noisy images and generates fake clean images; and the adversarial learning module, which differentiates between real and fake clean images through adversarial training. The complexity of NIL is significantly lower than that of previous unpaired methods, utilizing only one generator and one discriminator for training.Main results.By efficiently fusing unpaired images and employing adversarial training, NIL can extract more speckle noise information to enhance denoising performance. Building on NIL, we propose an OCT image denoising pipeline, NIL-NAFNet. This pipeline achieved PSNR, SSIM, and RMSE values of 31.27 dB, 0.865, and 7.00, respectively, on the PKU37 dataset. Extensive experiments suggest that our method outperforms state-of-the-art unpaired methods both qualitatively and quantitatively.Significance.These findings indicate that the proposed NIL is a simple yet effective method for unpaired OCT speckle noise reduction. The OCT denoising pipeline based on NIL demonstrates exceptional performance and efficiency. By addressing speckle noise without requiring well-registered image pairs, this method can enhance image quality and diagnostic accuracy in clinical practice.