Explore the vast range of titles available.

Image deblurring is a classic problem in low-level computer vision with the aim to recover a sharp image from a blurred input image. Advances in deep learning have led to significant progress in solving this problem, and a large number of deblurring networks have been proposed. This paper presents a comprehensive and timely survey of recently published deep-learning based image deblurring approaches, aiming to serve the community as a useful literature review. We start by discussing common causes of image blur, introduce benchmark datasets and performance metrics, and summarize different problem formulations. Next, we present a taxonomy of methods using convolutional neural networks (CNN) based on architecture, loss function, and application, offering a detailed review and comparison. In addition, we discuss some domain-specific deblurring applications including face images, text, and stereo image pairs. We conclude by discussing key challenges and future research directions.

Precipitation nowcasting, the high-resolution forecasting of precipitation up to two hours ahead, supports the real-world socioeconomic needs of many sectors reliant on weather-dependent decision-making 1 , 2 . State-of-the-art operational nowcasting methods typically advect precipitation fields with radar-based wind estimates, and struggle to capture important non-linear events such as convective initiations 3 , 4 . Recently introduced deep learning methods use radar to directly predict future rain rates, free of physical constraints 5 , 6 . While they accurately predict low-intensity rainfall, their operational utility is limited because their lack of constraints produces blurry nowcasts at longer lead times, yielding poor performance on rarer medium-to-heavy rain events. Here we present a deep generative model for the probabilistic nowcasting of precipitation from radar that addresses these challenges. Using statistical, economic and cognitive measures, we show that our method provides improved forecast quality, forecast consistency and forecast value. Our model produces realistic and spatiotemporally consistent predictions over regions up to 1,536 km × 1,280 km and with lead times from 5–90 min ahead. Using a systematic evaluation by more than 50 expert meteorologists, we show that our generative model ranked first for its accuracy and usefulness in 89% of cases against two competitive methods. When verified quantitatively, these nowcasts are skillful without resorting to blurring. We show that generative nowcasting can provide probabilistic predictions that improve forecast value and support operational utility, and at resolutions and lead times where alternative methods struggle. A deep generative model using radar observations is used to create skilful precipitation predictions that are accurate and support real-world utility.

Generalist methods for cellular segmentation have good out-of-the-box performance on a variety of image types; however, existing methods struggle for images that are degraded by noise, blurring or undersampling, all of which are common in microscopy. We focused the development of Cellpose3 on addressing these cases and here we demonstrate substantial out-of-the-box gains in segmentation and image quality for noisy, blurry and undersampled images. Unlike previous approaches that train models to restore pixel values, we trained Cellpose3 to output images that are well segmented by a generalist segmentation model, while maintaining perceptual similarity to the target images. Furthermore, we trained the restoration models on a large, varied collection of datasets, thus ensuring good generalization to user images. We provide these tools as ‘one-click’ buttons inside the graphical interface of Cellpose as well as in the Cellpose API. Cellpose3 employs deep-learning-based approaches for image restoration to improve cellular segmentation and shows strong generalized performance even on images degraded by noise, blurring or undersampling.

The 3D reconstruction using deep learning-based intelligent systems can provide great help for measuring an individual’s height and shape quickly and accurately through 2D motion-blurred images. Generally, during the acquisition of images in real-time, motion blur, caused by camera shaking or human motion, appears. Deep learning-based intelligent control applied in vision can help us solve the problem. To this end, we propose a 3D reconstruction method for motion-blurred images using deep learning. First, we develop a BF-WGAN algorithm that combines the bilateral filtering (BF) denoising theory with a Wasserstein generative adversarial network (WGAN) to remove motion blur. The bilateral filter denoising algorithm is used to remove the noise and to retain the details of the blurred image. Then, the blurred image and the corresponding sharp image are input into the WGAN. This algorithm distinguishes the motion-blurred image from the corresponding sharp image according to the WGAN loss and perceptual loss functions. Next, we use the deblurred images generated by the BF-WGAN algorithm for 3D reconstruction. We propose a threshold optimization random sample consensus (TO-RANSAC) algorithm that can remove the wrong relationship between two views in the 3D reconstructed model relatively accurately. Compared with the traditional RANSAC algorithm, the TO-RANSAC algorithm can adjust the threshold adaptively, which improves the accuracy of the 3D reconstruction results. The experimental results show that our BF-WGAN algorithm has a better deblurring effect and higher efficiency than do other representative algorithms. In addition, the TO-RANSAC algorithm yields a calculation accuracy considerably higher than that of the traditional RANSAC algorithm.

Objective This article examines whether performing location‐based platform work is associated with greater work–family conflict—and if this association is stronger for those relying on labor platforms for their primary employment. Background Digital labor platforms project a vision of flexibility and improved work‐family balance for workers; however, empirical evidence supporting these promises remains elusive. While platform workers are normally offered the freedom to choose their work hours, the efforts of labor platforms to algorithmically manage workers' schedules may encourage an ‘always‐on’ approach to work that pressures workers to prioritize work availability that exacerbates work–family conflicts. Method We conducted three national surveys of Canadian workers in 2020, 2021, and 2022. Based on pooled survey data (N = 10,483), structural equational modeling was used to investigate (1) the relationship between location‐based platform work and work–family conflict and (2) the mediating role of work‐family role blurring—captured by work contact outside of normal working hours. Results We discovered that platform workers, compared to employees and the traditional self‐employed, reported greater work–family conflict—conflicts that were especially pronounced for those relying on labor platforms as their primary source of income. These patterns were partially explained by platform workers' increased exposure to work contact outside of work hours. Conclusion Our findings question the assertion that digital labor platforms provide enhanced flexibility for managing work and family demands. Instead, we contend that the instability inherent in platform work blurs and disrupts work‐family role boundaries, disproportionately favoring labor platforms and their clientele at the expense of workers' familial responsibilities.

Images can be maliciously manipulated to hide content or duplicate certain objects. Detecting an elaborate copy-move forgery is very challenging for both humans and machines, and current methods cannot detect copy-move images with the precision required, especially for pixel-level tampered images, which is a challenge for the current existing methods. In this paper we present our own dataset (CMF58K) - the first pixel-level copy-move dataset, which consists of 580,000 images covering copy-move tampered objects in various life scenes with more than 32 object classes. Furthermore, we propose a network for detecting and locating copy-move forgeries: Efficient and Robust Identification Network (ERINet). It mainly includes four main modules: the efficient feature pyramid network (EFPN), the residual receptive field block (RRFB), the hierarchical decoding identification (HDI), and the cascaded group-reversal attention (GRA) blocks. Considering the inevitable external factors of rotation, scaling, blurring, compression and noise can hide traces of tampering and increase the difficulty of detection, we applied MaxBlurPool to our network and obtained a strong robustness. ERINet outperforms various state-of-the-art manipulation detection baselines on four image manipulation datasets. The inference speed is ∼ 49 fps on a single GPU without I/O time on the test dataset.

The development of a real-time and robust RGB-T tracker is an extremely challenging task because the tracked object may suffer from shared and specific challenges in RGB and thermal (T) modalities. In this work, we observe that the implicit attribute information can boost the model discriminability, and propose a novel attribute-driven representation network to improve the RGB-T tracking performance. First, according to appearance change in RGB-T tracking scenarios, we divide the major and special challenges into four typical attributes: extreme illumination, occlusion, motion blur, and thermal crossover. Second, we design an attribute-driven residual branch for each heterogeneous attribute to mine the attribute-specific property and therefore build a powerful residual representation for object modeling. Furthermore, we aggregate these representations in channel and pixel levels by using the proposed attribute ensemble network (AENet) to adaptively fit the attribute-agnostic tracking process. The AENet can effectively make aware of appearance change while suppressing the distractors. Finally, we conduct numerous experiments on three RGB-T tracking benchmarks to compare the proposed trackers with other state-of-the-art methods. Experimental results show that our tracker achieves very competitive results with a real-time tracking speed. Code will be available at https://github.com/zhang-pengyu/ADRNet.

Localizing human brain functions is a long-standing goal in systems neuroscience. Toward this goal, neuroimaging studies have traditionally used volume-based smoothing, registered data to volume-based standard spaces, and reported results relative to volume-based parcellations. A novel 360-area surface-based cortical parcellation was recently generated using multimodal data from the Human Connectome Project, and a volume-based version of this parcellation has frequently been requested for use with traditional volume-based analyses. However, given the major methodological differences between traditional volumetric and Human Connectome Project-style processing, the utility and interpretability of such an altered parcellation must first be established. By starting from automatically generated individual-subject parcellations and processing them with different methodological approaches, we show that traditional processing steps, especially volume-based smoothing and registration, substantially degrade cortical area localization compared with surface-based approaches. We also show that surface-based registration using features closely tied to cortical areas, rather than to folding patterns alone, improves the alignment of areas, and that the benefits of high-resolution acquisitions are largely unexploited by traditional volume-based methods. Quantitatively, we show that the most common version of the traditional approach has spatial localization that is only 35% as good as the best surface-based method as assessed using two objective measures (peak areal probabilities and “captured area fraction” for maximum probability maps). Finally, we demonstrate that substantial challenges exist when attempting to accurately represent volume-based group analysis results on the surface, which has important implications for the interpretability of studies, both past and future, that use these volume-based methods.

Non-Line-Of-Sight (NLOS) imaging aims at recovering the 3D geometry of objects that are hidden from the direct line of sight. One major challenge with this technique is the weak available multibounce signal limiting scene size, capture speed, and reconstruction quality. To overcome this obstacle, we introduce a multipixel time-of-flight non-line-of-sight imaging method combining specifically designed Single Photon Avalanche Diode (SPAD) array detectors with a fast reconstruction algorithm that captures and reconstructs live low-latency videos of non-line-of-sight scenes with natural non-retroreflective objects. We develop a model of the signal-to-noise-ratio of non-line-of-sight imaging and use it to devise a method that reconstructs the scene such that signal-to-noise-ratio, motion blur, angular resolution, and depth resolution are all independent of scene depth suggesting that reconstruction of very large scenes may be possible. Non-line-of-sight imaging can recover the 3D geometry of hidden objects, but is limited by weak multibounce signals. Here, the authors introduce a multipixel time-of-flight NLOS imaging approach, combining array detectors and a fast algorithm, for live reconstruction of natural nonretroreflective objects.