-
Cloud-removal-from-solar-imagery
The dataset used for removing cloud shadows from ground-based solar imagery. -
VIGOR dataset
The VIGOR dataset contains images of buildings and streets from different angles and lighting conditions. -
Real-world dataset for SCINeRF
This dataset is used to validate the effectiveness of the SCINeRF method for recovering 3D scenes from a single snapshot compressed image. -
Synthetic datasets for SCINeRF
This dataset is used to validate the effectiveness of the SCINeRF method for recovering 3D scenes from a single snapshot compressed image. -
Counting Objects by Diffused Index
Counting objects is a fundamental but challenging problem. In this paper, we propose diffusion-based, geometry-free, and learning-free methodologies to count the number of... -
PartImageNet
The PartImageNet dataset is a large-scale vehicle part segmentation dataset, containing 24,000 images of 158 classes. -
MPI Sintel
The dataset used in the paper for unsupervised single image intrinsic decomposition. -
OAMatcher: An Overlapping Areas-based Network for Accurate Local Feature Matc...
Local feature matching is an essential component in many visual applications. In this work, we propose OAMatcher, a detector-free method that imitates humans behavior to realize... -
The Robustness Limits of SoTA Vision Models to Natural Variation
A dataset of more than 7 million images with controlled changes in pose, position, background, lighting color, and size. -
Middlebury
The Middlebury dataset is a benchmark for stereo vision and 3D reconstruction. -
Tursun et al.'s dataset
Tursun et al.'s dataset is used for testing the proposed HDR-Transformer. -
Sen et al.'s dataset
Sen et al.'s dataset is used for testing the proposed HDR-Transformer. -
Kalantari et al.'s dataset
Kalantari et al.'s dataset consists of 74 samples for training and 15 samples for testing. -
Subject2Vec: Generative-Discriminative Approach from a Set of Image Patches t...
A deep learning model that learns subject-level representation from a set of local features. The model represents the image volume as a bag (or set) of local features and can... -
ObjectCompose
ObjectCompose: Evaluating Resilience of Vision-Based Models on Object-to-Background Compositional Changes -
Real-World Motion-Blurred Hand Dataset
A real-world dataset for motion-blurred hand extraction task. -
Synthetic Motion-Blurred Hand Dataset
A synthetic dataset for motion-blurred hand extraction task.