Cover Art Segmentation

## Overview

Cover Art Segmentation is a dataset for instance segmentation tasks - it contains Album Cover annotations for 680 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Context

Image Segmentation is a complicated problem that often cannot be performed in a fully automatic manner. We use this dataset as a way for testing and exploring methods to make such semi-automatic segmentation work better

Content

151 images with full segmentations and paint strokes (compiled by: http://www.robots.ox.ac.uk/~vgg/data/iseg/)

Acknowledgements

Visual Graphics Group at Oxford for Compiling the data GrabCut Dataset from Microsoft PASCAL Dataset Alpha Matting Dataset

Inspiration

• How well do different techniques work at expanding the initial labels to a full segmentation?
• Which techniques are quick enough to run in real time (the paint strokes are normally given and the user waits for feedback, they can't be precomputed)
• Are any of these techniques easy to implement in the JavaScript so they could be browser-based?

this project detect manhwa panale art then segment it

Custom2 Painting

## Overview

Custom2 Painting is a dataset for instance segmentation tasks - it contains Custom2 Painting annotations for 684 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [MIT license](https://creativecommons.org/licenses/MIT).

MuralDH Brief Summary The MuralDH dataset is a comprehensive collection of high-quality images for the digital restoration of Dunhuang murals. It includes over 5000 pre-processed images, curated to support research in digital art restoration, computer vision, and cultural heritage preservation. This dataset is divided into segments including damaged mural segmentation, high-resolution mural images, and images processed for super-resolution studies. The collection, designed to assist in the development and testing of digital restoration algorithms, aims to bridge traditional art with modern technology, ensuring the longevity and accessibility of these invaluable cultural treasures.Description of the Data and File Structure The dataset is structured as follows:Damaged Mural Segmentation Dataset: 1000 images annotated for specific types of damage such as cracks, flaking, and fading. Each file is named according to its specific damage type and contains annotations at the pixel level. High-Quality Mural Images: 500 images, each prepared for super-resolution processing. These are lower-resolution images that have been downscaled from the original high-resolution scans. Super-Resolution Dataset: A subset of the High-Quality Mural Images that have been further processed for super-resolution studies. Each image file is stored in PNG format, ensuring high-quality, lossless compression. Files are organized in folders corresponding to their dataset segment, and filenames follow a consistent naming convention to indicate their content and purpose.Missing data or incomplete images are marked with a specific code (e.g., NA for not available) in the accompanying metadata file. This file also provides a detailed description of each image, including its original location, the period it depicts, and any relevant historical or cultural notes.Sharing/Access Information The MuralDH dataset is hosted on Dryad but can also be accessed through the following link for direct download and further information:Data Derivation Sources This dataset was compiled from various sources, including digital archives and collaborations with cultural heritage organizations. Each image has been carefully selected and processed to meet the research needs while adhering to copyright and preservation guidelines.Code/Software The dataset comes with a set of Python scripts for basic image processing tasks, including image resizing, format conversion, and initial analysis.

With the increasing integration of functional imaging techniques like Positron Emission Tomography (PET) into radiotherapy (RT) practices, a paradigm shift in cancer treatment methodologies is underway. A fundamental step in RT planning is the accurate segmentation of tumours based on clinical diagnosis. Furthermore, novel tumour control methods, such as intensity modulated radiation therapy (IMRT) dose painting, demand the precise delineation of multiple intensity value contours to ensure optimal tumour dose distribution. Recently, convolutional neural networks (CNNs) have made significant strides in 3D image segmentation tasks, most of which present the output map at a voxel-wise level. However, because of information loss in subsequent downsampling layers, they frequently fail to precisely identify precise object boundaries. Moreover, in the context of dose painting strategies, there is an imperative need for reliable and precise image segmentation techniques to delineate high recurrence-risk contours. To address these challenges, we introduce a 3D coarse-to-fine framework, integrating a CNN with a kernel smoothing-based probability volume contour approach (KsPC). This integrated approach generates contour-based segmentation volumes, mimicking expert-level precision and providing accurate probability contours crucial for optimizing dose painting/IMRT strategies. Our final model, named KsPC-Net, leverages a CNN backbone to automatically learn parameters in the kernel smoothing process, thereby obviating the need for user-supplied tuning parameters. The 3D KsPC-Net exploits the strength of KsPC to simultaneously identify object boundaries and generate corresponding probability volume contours, which can be trained within an end-to-end framework. The proposed model has demonstrated promising performance, surpassing state-of-the-art models when tested against the MICCAI 2021 challenge dataset (HECKTOR).

Dataset

This dataset was created by Suryansh Gupta

Contents

The digital painting market is experiencing robust growth, driven by increasing demand for digital art across various applications, including gaming, animation, advertising, and fine art. The market's expansion is fueled by technological advancements in software and hardware, offering artists enhanced creative tools and accessibility. The rising adoption of digital platforms for art creation and distribution, coupled with the growing popularity of NFTs (Non-Fungible Tokens) and online art marketplaces, further contributes to market expansion. While precise figures are unavailable from the provided data, considering current market trends and the growth trajectory of related digital art sectors, a reasonable estimate for the 2025 market size could be placed at $2.5 billion USD. Assuming a conservative Compound Annual Growth Rate (CAGR) of 15% based on the dynamic nature of the digital art space, the market is projected to reach approximately $6.7 billion USD by 2033. This growth is expected to be driven by continuous technological innovation, increasing artist adoption, and expanding application in diverse sectors. Despite the positive outlook, market restraints include the need for specialized skills and software, the potential for copyright infringement issues surrounding digital art, and the ongoing debate regarding the valuation and authenticity of digital artwork. However, these challenges are likely to be mitigated by improvements in user-friendly software, stronger legal frameworks protecting digital artists' rights, and the increasing acceptance of digital art as a legitimate art form. The market segmentation includes various software types, hardware required for digital painting and the different application areas of the art created. Key players such as Meural, Mojarto, and several Chinese companies are actively shaping the market landscape through technological innovation and strategic partnerships.

Most semantic segmentation works have obtained accurate segmentation results through exploring the contextual dependencies. However, there are several major limitations that need further investigation. For example, most approaches rarely distinguish different types of contextual dependencies, which may pollute the scene understanding. Moreover, local convolutions are commonly used in deep learning models to learn attention and capture local patterns in the data. These convolutions operate on a small neighborhood of the input, focusing on nearby information and disregarding global structural patterns. To address these concerns, we propose a Global Domain Adaptation Attention with Data-Dependent Regulator (GDAAR) method to explore the contextual dependencies. Specifically, to effectively capture both the global distribution information and local appearance details, we suggest using a stacked relation approach. This involves incorporating the feature node itself and its pairwise affinities with all other feature nodes within the network, arranged in raster scan order. By doing so, we can learn a global domain adaptation attention mechanism. Meanwhile, to improve the features similarity belonging to the same segment region while keeping the discriminative power of features belonging to different segments, we design a data-dependent regulator to adjust the global domain adaptation attention on the feature map during inference. Extensive ablation studies demonstrate that our GDAAR better captures the global distribution information for the contextual dependencies and achieves the state-of-the-art performance on several popular benchmarks.

Discover the booming canvas painting kits market! Explore key trends, regional insights, and leading brands shaping this creative industry. Learn about market size, growth projections, and the opportunities within acrylic, oil, and watercolor painting kits.

The global art supplies for painting market is a vibrant and dynamic sector, exhibiting consistent growth driven by several key factors. Rising disposable incomes, particularly in developing economies, are fueling increased participation in painting as a hobby and professional pursuit. The burgeoning popularity of online art tutorials, social media art communities, and the accessibility of online art supply retailers are further boosting market expansion. Technological advancements in paint formulation, offering improved pigments, textures, and longevity, contribute significantly to market value. The market is segmented by application (e.g., fine art, hobbyist painting, commercial art) and type (e.g., acrylics, oils, watercolors, gouache), each exhibiting unique growth trajectories. For example, the demand for eco-friendly and sustainable art supplies is rapidly increasing, creating new opportunities for manufacturers focused on environmentally conscious products. While fluctuations in raw material prices and economic downturns can pose challenges, the overall market outlook remains positive, with a projected steady Compound Annual Growth Rate (CAGR). The market's regional distribution reflects varying levels of art appreciation and economic development. North America and Europe currently hold significant market share due to established art markets and high per capita disposable income. However, rapid growth is expected in Asia-Pacific regions like India and China, fueled by expanding middle classes and increasing interest in artistic expression. Competitive landscape analysis reveals a mix of established multinational corporations and smaller, specialized businesses catering to niche markets. Strategic collaborations, product innovation, and expansion into new geographical markets are key competitive strategies. The forecast period (2025-2033) anticipates continued market expansion, driven by the factors mentioned above, leading to substantial growth in market value. Understanding these trends and the specific needs of various market segments is crucial for success in this dynamic industry.

Dataset

This dataset was created by Shashil

Contents

Pictures Paintings And Digital Images

## Overview

Pictures Paintings And Digital Images is a dataset for instance segmentation tasks - it contains Pictures annotations for 1,408 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

The Paint Knife Market is estimated to be valued at USD 86.2 million in 2025 and is projected to reach USD 181.1 million by 2035, registering a compound annual growth rate (CAGR) of 7.7% over the forecast period.

The Industry Analysis Non-commercial Acrylic Paint in the United States is estimated to be valued at USD 312.8 million in 2025 and is projected to reach USD 485.7 million by 2035, registering a compound annual growth rate (CAGR) of 4.5% over the forecast period.

The Online Paint Editor App Market is estimated to be valued at USD 226.6 million in 2025 and is projected to reach USD 729.5 million by 2035, registering a compound annual growth rate (CAGR) of 12.4% over the forecast period.

Synthetic Faces High Quality (SFHQ) part 1

This dataset consists of 89,785 high quality 1024x1024 curated face images, and was created by "bringing to life" various art works (paintings, drawings, 3D models) using a process similar to what is described in this short twitter thread which involve encoding the images into StyleGAN2 latent space and performing a small manipulation that turns each image into a photo-realistic image.

The dataset also contains facial landmarks (extended set) and face parsing semantic segmentation maps. An example script is provided and demonstrates how to access landmarks, segmentation maps, and textually search withing the dataset (with CLIP image/text feature vectors), and also performs some exploratory analysis of the dataset. link to github repo of the dataset.

The process that "brings to life" paintings and creates several candidate photo-realistic images is illustrated below: https://i.ibb.co/6sykFrj/Figure-1.jpg" alt="">

More Details

1. The original inspiration images are taken from Artstation-Artistic-face-HQ Dataset (AAHQ) which contains mainly painting, drawing and 3D models of faces, Close-Up Humans Dataset that contains 3D models of faces and UIBVFED Dataset that also contain 3D models of faces.
2. Each inspiration image was encoded by encoder4editing (e4e) into StyleGAN2 latent space (StyleGAN2 is a generative face model tained on FFHQ dataset) and multiple candidate images were generated from each inspiration image
3. These candidate images were then further curated and verified as being photo-realistic and high quality by a single human (me) and a machine learning assistant model that was trained to approximate my own human judgments and helped me scale myself to asses the quality of all images in the dataset
4. Near duplicates and images that were too similar were removed using CLIP features (no two images in the dataset have CLIP similarity score of greater than ~0.92)
5. From each image various pre-trained features were extracted and provided here for convenience, in particular CLIP features for fast textual query of the dataset
6. From each image, semantic segmentation maps were extracted using Face Parsing BiSeNet and are provided in the dataset under "segmentations"
7. From each image, an extended landmark set was extracted that also contain inner and outer hairlines (these are unique landmarks that are usually not extracted by other algorithms). These landmarks were extracted using Dlib, Face Alignment and some post processing of Face Parsing BiSeNet and are provided in the dataset under "landmarks"
8. NOTE: semantic segmentation and landmarks were first calculated on scaled down version of 256x256 images, and then upscaled to 1024x1024

Parts 1,2,3,4

• Part 1 of the dataset consists of 89,785 HQ 1024x1024 curated face images. It uses "inspiration" images from Artstation-Artistic-face-HQ dataset (AAHQ), Close-Up Humans dataset and UIBVFED dataset.
• Part 2 of the dataset consists of 91,361 HQ 1024x1024 curated face images. It uses "inspiration" images from Face Synthetics dataset and by sampling from the Stable Diffusion v1.4 text to image generator using varied face portrait prompts.
• Part 3 of the dataset consists of 118,358 HQ 1024x1024 curated face images. It uses "inspiration" images by sampling from StyleGAN2 mapping network with very high truncation psi coefficients to increase diversity of the generation. Here, the e4e encoder is basically used a new kind of truncation trick.
• Part 4 of the dataset consists of 125,754 HQ 1024x1024 cur...

Considered are only tools with a graphical user interface since end users should not need programming expertise. Non deep learning segmentation methods may require expert knowledge for parametrization and are not state-of-the-art anymore. Data format support does not necessarily mean that each image can be processed: if no data management system (DMS) with metadata support is used, e.g., the channel dimension can be the first or the last dimension for.tif files, and the method may have requirements on the channel dimension position. ━: feature not fulfilled/supported, : feature only fulfilled/supported with restrictions, ✔: feature fulfilled/supported.

Discover the booming digital artwork market, projected to reach $15 billion by 2033 with a 20% CAGR. This in-depth analysis explores market trends, segmentation (digital painting, NFTs, etc.), key players, and regional growth, providing insights for investors and artists alike.