148 datasets found

The HPatches dataset is a benchmark dataset for local feature matching. It contains 108 sequences of 6 images each, with 52 sequences having illumination changes and 56...

MoSt-DSA is a dataset for direct multi-frame interpolation in DSA images. It contains 470 head DSA image sequences from 8 hospitals, each containing 152 images of 489x489...

The dataset contains aerial orthophotos in IRRG bands, nDSMs generated from LiDAR point clouds, and the corresponding semantic labels.

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.

A benchmark for evaluating hand pose tracking/estimation algorithms on passive stereo. Unlike existing benchmarks, it contains both stereo images from a binocular stereo camera...

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

The dataset used in this paper is a set of L x L images representing functions on [-1, 1]^2 supported on the disk {x ∈ R^2 : |x| < 1}. The images are digitized and the...

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.

A custom semi-automated visual inspection system has been implemented in the clean room for HGCAL sensor testing. The system uses a programmable xy-stage, the sensor is moved...

A container dynamic liquid level detection model based on U²-Net.

The dataset used for evaluating the performance of cloud removal methods.

The dataset used for evaluating the performance of cloud removal methods.

The dataset used for removing cloud shadows from ground-based solar imagery.

The VIGOR dataset contains images of buildings and streets from different angles and lighting conditions.

The Ford Multi AV dataset contains images of vehicles from different angles and lighting conditions.

Anomaly segmentation in images using Quantum Patch-Based Autoencoder (QPB-AE)