148 datasets found

InternLM-XComposer2-4KHD is a vision-language large model that supports images with any aspect ratio from 336 pixels up to 4K HD, facilitating its deployment in real-world...

The ceramic-3 test dataset used in the paper for contour matching and image processing tasks.

The dataset used in the paper for pattern matching and image processing tasks.

Microscopic images from the Broad Bioimage Benchmark Collection

Skeleton network library is used to extract line endpoints for each wall segment.

Change detection in high-resolution remote sensing images using a bitemporal image transformer (BIT)

WikiArts is a dataset of 63K images of paintings in HD, with 80-20% train-test split.

PuzzleCelebA is a dataset of 30K images of celebrities in High Definition (HD), with 80-20% train-test split.

The dataset used for training and testing the proposed LSSC system, which consists of 1530 training images and 170 test images in RGB format.

The dataset used in this paper is a hyperspectral image dataset, which is a type of multi-dimensional data. The dataset is used for tensor completion, a problem in scientific...

The dataset is used for evaluating the performance of fisheye image rectification algorithms. It contains real-world fisheye images with their corresponding ground truth images...

The dataset is used for fisheye image rectification. It contains synthetic images with fisheye distortion and their corresponding ground truth images, distortion parameters, and...

The Vaihingen dataset consists of 1440 scenes with a size of 250×250 pixels. Each scene is a colour-infrared (CIR) true orthophoto and a height grid (digital surface model; DSM)...

A dataset for inverting visual representations with convolutional networks.

The DIV2K dataset used for CT reconstruction.

The dataset used in the paper is a two-dimensional digital image processing dataset.

FashionAI: A Hierarchical Dataset for Fashion Understanding. This dataset comprises 180,335 apparel images. This dataset comprises 8 fashion attributes containing 55 classes each.

The dataset used for training and testing the proposed NICER approach for aesthetic image enhancement.

Low-light image enhancement has gained increasing importance with the rapid development of visual creation and editing. However, most existing enhancement algorithms are...

The MIT-Adobe FiveK dataset, a large-scale dataset for image segmentation and object detection.