102 datasets found

A fast, scalable, and reliable deghosting method for extreme exposure fusion.

An objective deghosting quality metric for HDR images.

Deep high dynamic range imaging of dynamic scenes.

Frame high dynamic range photography.

The FlyingThings3D dataset is a benchmark for stereo matching, consisting of a large collection of images and corresponding disparity maps.

Convolutional neural networks (CNNs) have become the state-of-the-art tool for dealing with unsolved problems in computer vision and image processing.

The DSIFN-CD dataset is a collection of high-resolution images with seasonal changes in different cities.

Describing Textures in the Wild dataset contains texture images with varying lighting conditions.

A dataset used for training and testing machine learning models for cerebral microbleeds detection.

The dataset consists of images with missing data, where the missing regions are simulated using different techniques such as square, trapezoid, and noise.

The dataset used in the paper is a benchmark dataset for visual SLAM, consisting of RGB-D images and IMU data.

The dataset used in the paper is a benchmark dataset for visual SLAM, consisting of RGB-D images and IMU data.

The dataset used in the paper is a benchmark dataset for visual SLAM, consisting of RGB-D images and IMU data.

The dataset used for training and testing the proposed DNN-based frame prediction architecture.

The JAFFE database consists of 213 images from 10 Japanese female subjects. For each subject, there are around 4 images for each of the seven expressions (including neutral).

HICO-Det is a benchmark for Human-Object Interaction (HOI) detection.

Human-Object Interaction (HOI) detection is a significant task to make a machine understand human activities in a static image at a fine-grained level.

Aerial images of London.

Street View images of London.

The CelebA-Mask-HQ dataset contains 30,000 HR faces with a size of 1024 × 1024 selected from the CelebA dataset.