-
Road Rutting Detection using Deep Learning on Images
A novel road rutting dataset containing 949 images from heterogeneous sources. -
LiqD: A Dynamic Liquid Level Detection Model
A container dynamic liquid level detection model based on U²-Net. -
Automated Deep Photo Style Transfer
Photorealism is a complex concept that cannot easily be formulated mathematically. Deep Photo Style Transfer is an attempt to transfer the style of a reference image to a... -
Visual Geo-localization from images
This paper presents a visual geo-localization system capable of determining the geographic locations of places (buildings and road intersections) from images without relying on... -
High Resolution Millimeter Wave Imaging For Self-Driving Cars
HawkEye is a system that can generate high resolution perceptually interpretable 2D depth-maps from 3D mmWave heat-maps for self-driving cars. -
ICPS-net dataset
A dataset created for training and testing the ICPS-net system for indoor positioning and navigation. -
Crowd Counting Datasets
The dataset used in the paper for crowd counting, which includes five challenging benchmarks: ShanghaiTech Part A & Part B (SHHA & SHHB), UCF-QNRF (QNRF), JHU-Crowd++... -
Adversarial Color Filter (AdvCF)
Adversarial Color Filter (AdvCF) is a novel color transformation attack that makes it possible to achieve non-suspicious adversarial images by optimizing a simple color filter. -
DarkFace [60]
Low-light image enhancement dataset -
ExDark [35]
Low-light image enhancement dataset -
REalistic Single Image DEhazing (RESIDE) dataset
The RESIDE dataset is a large-scale dataset for benchmarking single image dehazing algorithms, and it includes both indoor and outdoor hazy images. -
Chalearn LAP In-painting Competition Track 3 - Fingerprint Denoising and In-p...
The dataset provided by the organizers consisted of 84000 (200, 400) fingerprint images generated using Anguli: Synthetic Fingerprint Generator. Those images were then... -
Real-world dataset
The dataset used in this paper for testing the 3D-RecGAN++ model. It contains 1.5k SV and 2.5k CV testing datasets for each of the 6 categories. -
HDR+ dataset
A dataset of input/output image pairs for learning image enhancements -
MIT FiveK dataset
A dataset of input/output image pairs for learning photographic image enhancements -
WebCaricature dataset
The dataset used in the paper is the WebCaricature dataset, which contains 6,042 caricatures and 5,974 photographs from 252 persons.
