The Smartphone Image Denoising Dataset contains 160 pairs of noisy and ground-truth images captured from multiple smartphones (Google Pixel, iPhone 7, Samsung Galaxy S6 Edge, Nexus 6, and LG G4) under diverse lighting conditions. It is widely used in computational photography, image denoising, and AI research.

This dataset contains high-quality original images and their corresponding synthetically generated noisy variants using 7 common noise types: Gaussian, Speckle, Poisson, Multiplicative, JPEG Compression, Quantization, and Salt & Pepper. It's specifically designed to support the development, training, and benchmarking of deep learning models for image denoising, restoration, and computer vision tasks.

The noisy images were generated using Python and scikit-image, OpenCV, and NumPy, simulating realistic noise patterns that occur in real-world scenarios such as low-light imaging, compression artifacts, sensor defects, and quantization errors.

Ideal for training CNNs like U-Net, DnCNN, RIDNet, or for multi-noise classification tasks.

Each subfolder under noises/ contains synthetically altered images of the same IDs found in original/.

If you find this dataset useful, please star our repo and please cite the following works. Thank you. Chaudhary, Shivesh, Sihoon Moon, and Hang Lu. "Fast, efficient, and accurate neuro-imaging denoising via supervised deep learning." Nature communications 13.1 (2022): 5165.

Data description

TL;DR - a collection >5,000 of paired noisy and clean images to build deep learning denoising algorithms. Checkout getting_started notebook to quickly start training.

This is one of the largest dataset (>5000 images) of real low and high SNR images acquired using a confocal fluorescence microscope across three different cellular morphologies and labelling. Multiple noisy images corresponding to the same sample are also available thus the dataset can be used for building both supervised CARE, NIDDL, and unsupervised N2N, N2V methods. With this dataset we hope to drive development of new algorithms for image denoising.

1. Checkout the Key Features of the dataset below.
2. Checkout getting_started notebook for examples on how to collate data and build torch Dataset/Dataloaders.
3. Please take a look at the DataDescription.csv for description of various files.

Motivation

Fluorescence microscopy is an indispensable tool for biological discovery. But often scientist are only able to acquire noisy images. This is because of the imaging constraints of their experiments. E.g. whole-brain recording of neuron activities in C. elegans requires setting small exposure times and low lasers powers to perform volumetric imaging at high speed without causing photobleaching of fluorophores. The result is noisy images.

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F27405803%2F6ab3e9cdefdbbd1b26f4eb10297ce9fa%2Fwb_denoising.gif?generation=1750617078052388&alt=media" alt=""> Figure 1: Pan neuronal labelled head ganglion of C. elegans. Example shows noisy images and denoised images obtained by the baseline method. https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F27405803%2Fc9779c8f440924d79921a60dffcc8d7f%2Fneurite_denoising.gif?generation=1750619072029511&alt=media" alt=""> Figure 2 Neurites of the mechanosensory neuron PVD in C. elegans. Example shows noisy images and denoised images obtained by the baseline method.

1. Denoising fluorescence microscopy images can enable extraction of clean neuron activity traces from whole-brain recordings. Thus we need SOTA methods for denoising.
2. There are very few fluorescence microscopy datasets available for denoising task. The ones that are available are created synthetically by adding poisson and gaussian noise to clean images. In reality, noise in fluorescence microscopy images are much more complex.

Key Features

1. Data is available for 3 different kinds of cellular structures to test generalizability of algorithms across different kind morphologies

   • pan-neuronal labeled head ganglion neurons in C. elegans
   • ventral nerve motor neurons in C. elegans
   • Neurites of PVD neurons that show complex intricate morphology

2. Data is available for multiple signal-to-noise (SNR) levels to test limitations/capacities of algorithms across different amount of noises

   • e.g. in the dataset_20210226_denoising_ZIM504.h5, noisy and clean images were acquired using laser powers of 110 and 1000 settings at the microscope.
   • dataset_20210604_denoising_ZIM504.h5, noisy and clean images were acquired using laser powers of 75 and 1000 settings at the microscope.

3. For ventral-nerve datasets and PVD datasets, multiple noisy images for the same sample are present in the .5 files.

   • E.g. 20210710_denoising_PVD_array.h5 has two noisy images with keys noisy_1 and noisy_2 that were acquired at laser power settings of 200 and 400. Clean images are present under clean key and were acquired at laser power setting of 1000.
   • Thus dataset can be used to train both supervised denoising methods (using noisy and clean image pairs) or self-supervised algorithms like N2N (using noisy_1 and noisy_2 image pairs)

4. Both 3D image stacks (whole-brain) and 2D images (ventral-nerve and PVD-neurite) sample are present. Thus researcher can try exploring both 2D, 2.5D and 3D CNN denoising models

Baselines

Please check out simple baseline method NIDDL

Citation

**If you find this dataset useful, please star our repo and please cite the following works. Th...

Dataset

This dataset was created by Nicole Wheeler

Contents

We created a dataset - the Fluorescence Microscopy Denoising (FMD) dataset - that is dedicated to Poisson-Gaussian denoising. The dataset consists of 12,000 real fluorescence microscopy images obtained with commercial confocal, two-photon, and wide-field microscopes and representative biological samples such as BPAE cells, zebrafish, and mouse brain tissues. We use image averaging to effectively obtain ground truth images and 60,000 noisy images with different noise levels.

Image Denoising AI Market Outlook

According to our latest research, the global Image Denoising AI market size reached USD 1.42 billion in 2024, reflecting robust adoption across multiple industries. The market is projected to expand at a CAGR of 20.3% from 2025 to 2033, resulting in a forecasted market value of USD 8.36 billion by 2033. This remarkable growth is primarily driven by the increasing integration of artificial intelligence in imaging solutions, the proliferation of high-resolution imaging devices, and the growing demand for enhanced image quality in critical sectors such as healthcare, automotive, and security. As per our latest research, technological advancements and the need for real-time, noise-free image processing are further propelling the marketÂ’s upward trajectory.

The expansion of the Image Denoising AI market is fundamentally fueled by the exponential growth in digital imaging applications across diverse domains. In healthcare, for instance, the adoption of AI-powered denoising tools has significantly improved the accuracy of diagnostic imaging by reducing artifacts and enhancing clarity in MRI, CT, and X-ray scans. This has led to better patient outcomes and reduced the need for repeat imaging, thereby lowering costs and exposure to radiation. Furthermore, the increasing reliance on imaging technologies in autonomous vehicles, industrial automation, and smart surveillance systems has heightened the need for robust denoising solutions capable of delivering real-time, high-fidelity results even in challenging environments. The rapid evolution of deep learning algorithms and the availability of large annotated datasets have made AI-based denoising more accessible and effective, contributing to the accelerated market growth.

Another significant growth driver for the Image Denoising AI market is the proliferation of consumer electronics equipped with advanced imaging capabilities. Smartphones, digital cameras, and smart home devices now feature high-resolution sensors that are susceptible to noise, especially in low-light conditions. AI-powered denoising algorithms have become essential for manufacturers aiming to deliver superior image quality to end-users. Moreover, the rise of content creation for social media, digital marketing, and entertainment platforms has further amplified the demand for automated, seamless image enhancement tools. The integration of AI into edge devices, coupled with the growing trend of on-device processing, is enabling faster and more efficient denoising, reducing reliance on cloud resources and ensuring user privacy. These advancements are opening new avenues for market participants, particularly in the fast-evolving consumer electronics space.

The Image Denoising AI market is also benefiting from increased investments in research and development by both established players and emerging startups. Governments and private organizations are funding initiatives aimed at advancing AI-driven imaging technologies, fostering innovation and collaboration across academia and industry. This has resulted in the introduction of novel architectures and hybrid models that combine traditional signal processing techniques with deep neural networks, achieving unprecedented performance in noise reduction. Additionally, the adoption of AI denoising in sectors such as satellite imaging, digital forensics, and industrial inspection is expanding the addressable market, as organizations seek to extract actionable insights from noisy or degraded images. The ongoing push towards automation, efficiency, and accuracy in image-based workflows is expected to sustain high demand for AI-powered denoising solutions throughout the forecast period.

The implementation of Noise Suppression AI is becoming increasingly vital in the realm of image processing, particularly within the Image Denoising AI market. This advanced technology plays a crucial role in enhancing the clarity and quality of images by effectively reducing unwanted noise. As imaging devices become more sophisticated, the demand for noise suppression capabilities is growing, especially in applications where precision is paramount, such as medical imaging and autonomous vehicles. By integrating Noise Suppression AI, industries can achieve higher accuracy in image analysis, leading to improved decision-making and operational efficiency. This technology not only enhances visual quality but also supp

Dataset

This dataset was created by Mohamed khaled

Contents

Hyperspectral image denoising with realistic data

A New Method for Nonlocal Means Image Denoising Using Multiple Image

Quantum-Enhanced Image Denoising Market Outlook

According to our latest research, the global Quantum-Enhanced Image Denoising market size reached USD 182 million in 2024, with a robust compound annual growth rate (CAGR) of 38.1% projected through the forecast period. By 2033, the market is expected to achieve a value of USD 2.78 billion, underscoring the rapid adoption of quantum technologies for advanced image processing. This surge is primarily driven by increasing demand for high-fidelity imaging across industries, coupled with the ongoing advancements in quantum computing and machine learning integration. As per our latest research, the market is experiencing significant momentum due to the convergence of quantum algorithms and artificial intelligence, which is revolutionizing the landscape of image denoising.

The primary growth factor for the Quantum-Enhanced Image Denoising market is the escalating need for superior image clarity in mission-critical applications such as medical diagnostics, satellite imagery, and industrial quality control. Traditional image denoising techniques, while effective to a certain extent, often fall short when handling high-noise environments or when tasked with preserving minute details. Quantum-enhanced approaches leverage quantum superposition and entanglement to process vast datasets in parallel, resulting in unprecedented speed and accuracy. This technological leap is particularly vital in healthcare, where early and accurate detection of anomalies in medical images can directly impact patient outcomes. Additionally, the proliferation of high-resolution imaging sensors and the exponential growth of data generated by these devices are compelling organizations to adopt quantum-enhanced solutions to maintain competitive advantage.

Another significant driver is the growing integration of quantum machine learning algorithms with conventional image processing pipelines. Quantum algorithms, such as quantum support vector machines and quantum neural networks, are demonstrating marked improvements in denoising performance, especially in low-light or high-noise scenarios. These advancements are not limited to healthcare; industries such as aerospace, defense, and manufacturing are increasingly investing in quantum-enhanced denoising to improve the accuracy of defect detection, surveillance, and remote sensing. The quantum advantage in processing speed and the ability to handle complex, multidimensional data are opening new possibilities for real-time applications, further fueling market growth.

The market is also benefitting from substantial investments by both public and private sectors in quantum technology research and development. Governments and leading technology companies are allocating significant resources to accelerate the commercialization of quantum computing, which directly supports the evolution of quantum-enhanced image denoising solutions. Collaborative initiatives between academia, industry, and government agencies are fostering innovation and driving the deployment of pilot projects across various sectors. Moreover, the increasing accessibility of cloud-based quantum computing platforms is democratizing the adoption of quantum-enhanced image denoising, enabling even small and medium-sized enterprises to leverage cutting-edge technology without substantial capital expenditure.

From a regional perspective, North America currently dominates the Quantum-Enhanced Image Denoising market, accounting for the largest share in 2024, followed closely by Europe and the Asia Pacific region. The robust ecosystem of quantum technology startups, strong academic research infrastructure, and significant government funding in the United States and Canada are key contributors to North America's leadership. Meanwhile, Europe is witnessing rapid growth due to strategic collaborations and a focus on industrial automation and healthcare innovation. The Asia Pacific region, led by China, Japan, and South Korea, is emerging as a hotbed for quantum research, with increasing investments in quantum computing infrastructure and a growing demand for advanced imaging across manufacturing and automotive sectors. These regional dynamics are shaping the global competitive landscape and influencing market trajectories.

In the realm of video technology, <a href="https://growthmarketreports.com/report/quantum-assisted-video-compression-marke

Dataset

This dataset was created by Ronnie-Leon76

Contents

This dataset provides 8,643 abnormal images and videos covering 14 different distortion types, including noise, blur, low resolution, and other degradations.The data includes indoor scenes (library, craft store, etc.) and outdoor scenes (road, building, square, railway station, etc.) under various lighting conditions and resolutions. This dataset can be used for tasks such as image denoising, image deblurring, low-light enhancement, and real-world degraded image reconstruction.

Images often contain noise due to imperfections in various image acquisition techniques. Noise should be removed from images so that the details of image objects (e.g., blood vessels, inner foldings, or tumors in the human brain) can be clearly seen, and the subsequent image analyses are reliable. With broad usage of images in many disciplines—for example, medical science—image denoising has become an important research area. In the literature, there are many different types of image denoising techniques, most of which aim to preserve image features, such as edges and edge structures, by estimating them explicitly or implicitly. Techniques based on explicit edge detection usually require certain assumptions on the smoothness of the image intensity surface and the edge curves which are often invalid especially when the image resolution is low. Methods that are based on implicit edge detection often use multiresolution smoothing, weighted local smoothing, and so forth. For such methods, the task of determining the correct image resolution or choosing a reasonable weight function is challenging. If the edge structure of an image is complicated or the image has many details, then these methods would blur such details. This article presents a novel image denoising framework based on local clustering of image intensities and adaptive smoothing. The new denoising method can preserve complicated edge structures well even if the image resolution is low. Theoretical properties and numerical studies show that it works well in various applications.

Image Denoising AI Market Outlook

According to our latest research, the global Image Denoising AI market size reached USD 1.14 billion in 2024, with a robust compound annual growth rate (CAGR) of 27.6% expected from 2025 to 2033. By 2033, the market is forecasted to reach USD 10.65 billion, propelled by increasing adoption of artificial intelligence in imaging applications and rapid advancements in deep learning algorithms. The primary growth drivers include the rising need for high-quality image processing across diverse sectors and the surging demand for automation in visual content enhancement.

One of the key growth factors for the Image Denoising AI market is the exponential increase in the volume of digital images generated across industries such as healthcare, automotive, and consumer electronics. With the proliferation of high-resolution imaging devices and the growing importance of image-based data in diagnostics, surveillance, and entertainment, organizations are seeking advanced AI-powered solutions to remove noise and improve image clarity. This trend is further fueled by the integration of AI in imaging workflows, enabling real-time and automated denoising capabilities that significantly enhance operational efficiency and accuracy. Additionally, the advent of edge computing and the need for low-latency image processing are catalyzing the deployment of AI-driven denoising algorithms on a wide array of devices, from medical scanners to smartphones and autonomous vehicles.

Another significant driver is the remarkable progress in AI technologies, particularly in deep learning architectures such as convolutional neural networks (CNNs), generative adversarial networks (GANs), and autoencoders. These advancements have enabled the development of sophisticated denoising models that can effectively differentiate between noise and meaningful image content, delivering superior results compared to traditional filtering techniques. The research community and industry leaders are investing heavily in R&D to further refine these models, making them more robust and adaptable to various noise profiles and imaging modalities. Furthermore, the growing availability of large annotated datasets and the rise of transfer learning have accelerated the training and deployment of denoising AI models, expanding their applicability across new domains and use cases.

The surge in demand for high-quality imaging in emerging applications such as autonomous driving, industrial inspection, and next-generation medical diagnostics is also contributing to market expansion. In automotive, for instance, the reliability of computer vision systems is paramount for safety-critical tasks, necessitating advanced denoising solutions to handle challenging environmental conditions. Similarly, in healthcare, the precision of AI-powered denoising directly impacts the accuracy of diagnostic imaging, leading to improved patient outcomes. The increasing adoption of AI-based denoising in consumer electronics, including smartphones and digital cameras, is further broadening the market landscape, as end-users seek enhanced photography experiences and content creation capabilities.

From a regional perspective, North America continues to dominate the Image Denoising AI market, accounting for the largest revenue share in 2024, primarily due to the strong presence of leading AI technology providers, advanced healthcare infrastructure, and significant investments in R&D. Asia Pacific is emerging as the fastest-growing region, driven by rapid digitalization, expanding industrial automation, and increasing adoption of AI in imaging applications across countries such as China, Japan, and South Korea. Europe is also witnessing substantial growth, supported by the region’s focus on innovation in automotive and industrial sectors. Overall, the global landscape is characterized by dynamic regional shifts and a growing emphasis on cross-industry collaboration to unlock the full potential of AI-powered image denoising.

Component Analysis

The Component segment of the Image Denoising AI market is broadly categorized into software, hardware, and services, each playing a pivotal role in shaping the overall ecosystem. Software solutions dominate the market, accounting for the highest revenue share in 2024, as organizations prioritize the integration of advanced denoising algorithms into their imaging workflows. These software offerings rang

a algorithm workflow for high quality DACs HAADF-STEM image denoising and identification

Yearly citation counts for the publication titled "A Comparative Analysis of Image Denoising Filters for Salt and Pepper Noise".

Yearly citation counts for the publication titled "Digital Image Denoising Techniques Based on Multi-Resolution Wavelet Domain with Spatial Filters: A Review".

Extreme low-light denoising (ELD) dataset that covers 10 indoor scenes and 4 camera devices from multiple brands (SonyA7S2, NikonD850, CanonEOS70D, CanonEOS700D). It has three levels (800, 1600, 3200) and two low light factors(100, 200) for noisy images, resulting in 240 (3×2×10×4) raw image pairs in total.

The dataset used for training and testing deep neural networks-based denoising models for CT imaging.

Yearly citation counts for the publication titled "Multiscale LMMSE-based image denoising with optimal wavelet selection".