-
Harmonic Decompositions of Convolutional Networks
The dataset used in this paper is a collection of images of faces, each with a different expression. -
XAMI - A Benchmark Dataset for Artefact Detection in XMM-Newton Optical Images
A dataset of images from the XMM-Newton space telescope Optical Monitoring camera showing different types of artefacts. -
Machine-learned 3D building vectorization from satellite imagery
Machine-learned 3D building vectorization from satellite imagery. -
Baseball Dataset
A comprehensive baseball dataset comprising over 1000 games, including more than 100,000 pitches. -
Adversarial Data Programming: Using GANs to Relax the Bottleneck of Curated L...
Paucity of large curated hand-labeled training data for every domain-of-interest forms a major bottleneck in the deployment of machine learning models in computer vision and... -
CNN Fixations: An unraveling approach to visualize the discriminative image r...
The proposed approach is demonstrated on multiple vision tasks and modalities through a variety of applications. -
KITTI odometry benchmark dataset
The KITTI odometry benchmark dataset is used for evaluating computer vision algorithms in autonomous driving scenarios. It contains LiDAR data collected with Velodyne HDL-64E,... -
Dense Depth Posterior (DDP) from Single Image and Sparse Range
A deep learning system to infer the posterior distribution of a dense depth map associated with an image, by exploiting sparse range measurements. -
Optical Flow Based Real-time Moving Object Detection in Unconstrained Scenes
Real-time moving object detection in unconstrained scenes -
Minimal Solvers for Rectifying from Radially-Distorted Scales and Change of S...
The proposed minimal solvers exploit the scale constraint: two instances of rigidly-transformed coplanar repeats occupy identical areas in the scene plane and in the rectified... -
Epipolar Line Segmentation
The dataset used in the paper for feature correspondence between two images, using the epipolar line and cheirality constraint. -
SIFT1M and GIST1M
The dataset used in this paper is SIFT1M and GIST1M, two large-scale image datasets. -
ImageNet Dense Connectivity Space
The dataset used in the paper is an ImageNet dense connectivity design space for CNN architectures. -
CIFAR-10 Dense Connectivity Space
The dataset used in the paper is a dense connectivity design space for CNN architectures. -
SynthImageNet
The dataset used in the paper for representation learning through latent canonicalizations. -
Geometric Simple Shape (GSS) dataset
The dataset is designed to minimize potential disruptions arising from an excess of information during focus analysis. -
Homography estimation
Homography estimation serves as a fundamental technique for image alignment in a wide array of applications.
