Explore the vast range of titles available.

Image rescaling is a commonly used bidirectional operation, which first downscales high-resolution images to fit various display screens or to be storage- and bandwidth-friendly, and afterward upscales the corresponding low-resolution images to recover the original resolution or the details in the zoom-in images. However, the non-injective downscaling mapping discards high-frequency contents, leading to the ill-posed problem for the inverse restoration task. This can be abstracted as a general image degradation–restoration problem with information loss. In this work, we propose a novel invertible framework to handle this general problem, which models the bidirectional degradation and restoration from a new perspective, i.e. invertible bijective transformation. The invertibility enables the framework to model the information loss of pre-degradation in the form of distribution, which could mitigate the ill-posed problem during post-restoration. To be specific, we develop invertible models to generate valid degraded images and meanwhile transform the distribution of lost contents to the fixed distribution of a latent variable during the forward degradation. Then restoration is made tractable by applying the inverse transformation on the generated degraded image together with a randomly-drawn latent variable. We start from image rescaling and instantiate the model as Invertible Rescaling Network, which can be easily extended to the similar decolorization–colorization task. We further propose to combine the invertible framework with existing degradation methods such as image compression for wider applications. Experimental results demonstrate the significant improvement of our model over existing methods in terms of both quantitative and qualitative evaluations of upscaling and colorizing reconstruction from downscaled and decolorized images, and rate-distortion of image compression. Code is available at https://github.com/pkuxmq/Invertible-Image-Rescaling.

Human Pose Estimation (HPE) models have varied applications and represent a cutting-edge branch of study, whose systems such as MediaPipe (MP), OpenPose (OP), and AlphaPose (ALP) show marked success. One of these areas, however, that is inadequately researched is the impact of image degradation on the accuracy of HPE models. Image degradation refers to images whose visual quality has been purposefully degraded by means of techniques, such as brightness adjustments (which can lead to an increase or a decrease in the intensity levels), geometric rotations, or resolution downscaling. The study of how these types of degradation impact the performance functionality of HPE models is an under-researched domaina that is a virtually unexplored area. In addition, current methods of the efficacy of existing image restoration techniques have not been rigorously evaluated and improving degraded images to a high quality has not been well examined in relation to improving HPE models. In this study, we explicitly clearly demonstrate a decline in the precision of the HPE model when image quality is degraded. Our qualitative and quantitative measurements identify a wide difference in performance in identifying landmarks as images undergo changes in brightness, rotation, or reductions in resolution. Additionally, we have tested a variety of existing image enhancement methods in an attempt to enhance their capability in restoring low-quality images, hence supporting improved functionality of HPE. Interestingly, for rotated images, using Pillow of OpenCV improves landmark recognition precision drastically, nearly restoring it to levels we see in high-quality images. In instances of brightness variation and in low-quality images, however, existing methods of enhancement fail to yield the improvements anticipated, highlighting a large direction of study that warrants further investigation and calls for additional research. In this regard, we proposed a wide-ranging system for classifying different types of image degradation systematically and for selecting appropriate algorithms for image restoration, in an effort to restore image quality. A key finding is that in a related study of current methods, the Tuned RotNet model achieves 92.04% accuracy, significantly outperforming the baseline model and surpassing the official RotNet model in predicting rotation degree of images, where the accuracy of official RotNet and Tuned RotNet classifiers were 61.59% and 92.04%, respectively. Furthermore, in an effort to facilitate future research and make it easier for other studies, we provide a new dataset of reference images and corresponding degenerated images, addressing a notable gap in controlled comparative studies, since currently there is a lack of controlled comparatives.

Because the real degradation model is more complex, and the different computing performance of devices leads to different degradation results. The super-resolution based on the real image degradation model has great challenges in practical applications. To solve these problems, we propose a novel SR network based on self-calibration convolution and adaptive dense connection (SCCADC-SR). Firstly, we introduce self-calibration convolution as the basic convolution module and use it as a supplement to the attention mechanism. Secondly, we use efficient channel attention (ECA) to construct an adaptive dense connection structure to deal with the features at the different levels. Then, we use the CutBlur method to enhance the data to improve the generalization ability of the model and use the long skip connection to improve the convergence of the depth model structure. Finally, SCCADC-SR combines self-ensemble and model ensemble to improve the model’s robustness and reduce the noise. Experimental results show that for both real image data and Bicubic data, our SCCADC-SR improves SR reconstruction performance by 5% compared with the state-of-the-art methods.

This paper proposes IFEM-YOLOv13, a high-precision underwater target detection method designed to address challenges such as image degradation, low contrast, and small target obscurity caused by light attenuation, scattering, and biofouling. Its core innovation is an end-to-end degradation-aware system featuring: (1) an Intelligent Feature Enhancement Module (IFEM) that employs learnable sharpening and pixel-level filtering for adaptive optical compensation, incorporating principles of symmetry in its multi-branch enhancement to balance color and structural recovery; (2) a degradation-aware Focal Loss incorporating dynamic gradient remapping and class balancing to mitigate sample imbalance through symmetry-preserving optimization; and (3) a cross-layer feature association mechanism for multi-scale contextual modeling that respects the inherent scale symmetry of natural objects. Evaluated on the J-EDI dataset, IFEM-YOLOv13 achieves 98.6% mAP@0.5 and 82.1% mAP@0.5:0.95, outperforming the baseline YOLOv13 by 0.7% and 3.0%, respectively. With only 2.5 M parameters and operating at 217 FPS, it surpasses methods including Faster R-CNN, YOLO variants, and RE-DETR. These results demonstrate its robust real-time detection capability for diverse underwater targets such as plastic debris, biofouled objects, and artificial structures, while effectively handling the symmetry-breaking distortions introduced by the underwater environment.

Frame buildings as important nodes of urban space. The include high-speed railway stations, airports, residences, and office buildings, which carry various activities and functions. Due to illumination irrationality and mutual occlusion between complex objects, low illumination situations frequently develop in these architectural environments. In this case, the location information of the target is difficult to determine. At the same time, the change in the indoor electromagnetic environment also affects the location information of the target. Therefore, this paper adopts the vision method to achieve target localization in low-illumination environments by feature matching of images collected in the offline state. However, the acquired images have serious quality degradation problems in low-illumination conditions, such as low brightness, low contrast, color distortion, and noise interference. These problems mean that the local features in the collected images are missing, meaning that they fail to achieve a match with the offline database images; as a result, the location information of the target cannot be determined. Therefore, a Visual Localization with Multiple-Similarity Fusions (VLMSF) is proposed based on the Nonlinear Enhancement And Local Mean Filtering (NEALMF) preprocessing enhancement. The NEALMF method solves the problem of missing local features by improving the quality of the acquired images, thus improving the robustness of the visual positioning system. The VLMSF method solves the problem of low matching accuracy in similarity retrieval methods by effectively extracting and matching feature information. Experiments show that the average localization error of the VLMSF method is only 8 cm, which is 33.33% lower than that of the Kears-based VGG-16 similarity retrieval method. Meanwhile, the localization error is reduced by 75.76% compared with the Perceptual hash (Phash) retrieval method. The results show that the method proposed in this paper greatly alleviates the influence of low illumination on visual methods, thus helping city managers accurately grasp the location information of targets under complex illumination conditions.

Underwater image enhancement presents a significant challenge due to the complex and diverse underwater environments that result in severe degradation phenomena such as light absorption, scattering, and color distortion. More importantly, obtaining paired training data for these scenarios is a challenging task, which further hinders the generalization performance of enhancement models. To address these issues, we propose a novel approach, the Hybrid Contrastive Learning Regularization (HCLR-Net). Our method is built upon a distinctive hybrid contrastive learning regularization strategy that incorporates a unique methodology for constructing negative samples. This approach enables the network to develop a more robust sample distribution. Notably, we utilize non-paired data for both positive and negative samples, with negative samples are innovatively reconstructed using local patch perturbations. This strategy overcomes the constraints of relying solely on paired data, boosting the model’s potential for generalization. The HCLR-Net also incorporates an Adaptive Hybrid Attention module and a Detail Repair Branch for effective feature extraction and texture detail restoration, respectively. Comprehensive experiments demonstrate the superiority of our method, which shows substantial improvements over several state-of-the-art methods in terms of quantitative metrics, significantly enhances the visual quality of underwater images, establishing its innovative and practical applicability. Our code is available at: https://github.com/zhoujingchun03/HCLR-Net.

The deep image prior showed that a randomly initialized network with a suitable architecture can be trained to solve inverse imaging problems by simply optimizing it’s parameters to reconstruct a single degraded image. However, it suffers from two practical limitations. First, it remains unclear how to control the prior beyond the choice of the network architecture. Second, training requires an oracle stopping criterion as during the optimization the performance degrades after reaching an optimum value. To address these challenges we introduce a frequency-band correspondence measure to characterize the spectral bias of the deep image prior, where low-frequency image signals are learned faster and better than high-frequency counterparts. Based on our observations, we propose techniques to prevent the eventual performance degradation and accelerate convergence. We introduce a Lipschitz-controlled convolution layer and a Gaussian-controlled upsampling layer as plug-in replacements for layers used in the deep architectures. The experiments show that with these changes the performance does not degrade during optimization, relieving us from the need for an oracle stopping criterion. We further outline a stopping criterion to avoid superfluous computation. Finally, we show that our approach obtains favorable results compared to current approaches across various denoising, deblocking, inpainting, super-resolution and detail enhancement tasks. Code is available at https://github.com/shizenglin/Measure-and-Control-Spectral-Bias.

Structured illumination microscopy (SIM) surpasses the optical diffraction limit and offers a two-fold enhancement in resolution over diffraction limited microscopy. However, it requires both intense illumination and multiple acquisitions to produce a single high-resolution image. Using deep learning to augment SIM, we obtain a five-fold reduction in the number of raw images required for super-resolution SIM, and generate images under extreme low light conditions (at least 100× fewer photons). We validate the performance of deep neural networks on different cellular structures and achieve multi-color, live-cell super-resolution imaging with greatly reduced photobleaching. Super-resolution microscopy typically requires high laser powers which can induce photobleaching and degrade image quality. Here the authors augment structured illumination microscopy (SIM) with deep learning to reduce the number of raw images required and boost its performance under low light conditions.

This project explores EasyOCR’s performance with Latin characters under image degradation. Variables like character-background intensity difference, Gaussian blur, and relative character size were tested. EasyOCR excels in distinguishing unique lowercase and uppercase characters but tends to favor uppercase for similar shapes like C, S, U, or Z. Results showed that high character-background intensity differences affected OCR output, with confidence scores ranging from 3 % to 80%. Higher differences caused confusion between characters like o and 0, or i and 1. Increased Gaussian blur hindered recognition but improved it for certain letters like v. Image size had a significant impact, with character detection failing as sizes decreased to 40% to 30% of the original. These findings provide insights into EasyOCR’s capabilities and limitations with Latin characters under image degradation.

The capability of image deraining is a highly desirable component of intelligent decision-making in autonomous driving and outdoor surveillance systems. Image deraining aims to restore the clean scene from the degraded image captured in a rainy day. Although numerous single image deraining algorithms have been recently proposed, these algorithms are mainly evaluated using certain type of synthetic images, assuming a specific rain model, plus a few real images. It remains unclear how these algorithms would perform on rainy images acquired “in the wild” and how we could gauge the progress in the field. This paper aims to bridge this gap. We present a comprehensive study and evaluation of existing single image deraining algorithms, using a new large-scale benchmark consisting of both synthetic and real-world rainy images of various rain types. This dataset highlights diverse rain models (rain streak, rain drop, rain and mist), as well as a rich variety of evaluation criteria (full- and no-reference objective, subjective, and task-specific). We further provide a comprehensive suite of criteria for deraining algorithm evaluation, including full- and no-reference metrics, subjective evaluation, and the novel task-driven evaluation. The proposed benchmark is accompanied with extensive experimental results that facilitate the assessment of the state-of-the-arts on a quantitative basis. Our evaluation and analysis indicate the gap between the achievable performance on synthetic rainy images and the practical demand on real-world images. We show that, despite many advances, image deraining is still a largely open problem. The paper is concluded by summarizing our general observations, identifying open research challenges and pointing out future directions. Our code and dataset is publicly available at http://uee.me/ddQsw.