83 datasets found

The Point Grey Bumblebee2 1394a1 and the ZED Stereo Camera2 are used to evaluate the proposed stereo matching method.

The patch ordering method for image denoising uses √n by √n overlapping image patches.

A dataset of 13 full-length HRCT scans of varying thicknesses (0.67mm, 1mm, 2mm) used to test methods for detecting discrete broncho-arterial pairs and measuring...

The dataset used in the paper is a synthetic image dataset, consisting of 100 images with varying levels of noise.

The dataset used in the paper is a color image denoising dataset, consisting of 100 natural images with varying levels of noise.

The dataset used in this paper is a binary image with outliers. The dataset is used to test the proposed convex hull algorithm for images with outliers.

The dataset contains images from the INRIA Holidays dataset, with SIFT feature vectors extracted from the images.

A new semi-sparsity model for image structure-texture decomposition.

A dataset of 405 natural images with a minimum of one flare spot artifact, captured by different cameras with different technical specifications.

The Extended Yale B database consists of 2414 frontal-face images of 38 subjects. Each subject has around 64 images. The images are cropped and normalized to 192 × 168 under...

Wireframe is a dataset used to evaluate line segment detection and description algorithms.

VGGAffine is a dataset used to evaluate line segment detection algorithms.

This study comprehensively reviews numerous line segment detection and description algorithms to provide researchers with an overall picture and deep understanding of them.

Large-scale Visible Watermark Dataset (LVW) and Colored Large-scale Watermark Dataset (CLWD) for watermark removal task

The dataset used in the paper is the Kylberg texture database, which contains 240 fully-textured images belonging to 6 different substances.

The dataset used for training and testing the proposed Cascaded Edge and Image Learning Network (CEILNet) for single image reflection removal and image smoothing.

The dataset used in the paper is a compressed sensing problem – under-determined sparse recovery from linear Gaussian random measurements.

InternLM-XC 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 contexts.

InternLM2 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 contexts.

InternLM-XComposer2 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 contexts.