63 datasets found

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.

This dataset is used to validate the effectiveness of the SCINeRF method for recovering 3D scenes from a single snapshot compressed image.

This dataset is used to validate the effectiveness of the SCINeRF method for recovering 3D scenes from a single snapshot compressed image.

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...

The PartImageNet dataset is a large-scale vehicle part segmentation dataset, containing 24,000 images of 158 classes.

The KITTI360 dataset is used for evaluating the proposed Tuple-Circle loss function for cross-modality feature learning. The dataset consists of image and LiDAR scan pairs.

The dataset used in the paper for unsupervised single image intrinsic decomposition.

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...

A dataset of more than 7 million images with controlled changes in pose, position, background, lighting color, and size.

The Middlebury dataset is a benchmark for stereo vision and 3D reconstruction.

Synthetic rainy images dataset for training and testing the proposed LPNet for single image deraining.

The dataset for single image deraining, containing images with rain and their corresponding ground truth images.

Tursun et al.'s dataset is used for testing the proposed HDR-Transformer.

Sen et al.'s dataset is used for testing the proposed HDR-Transformer.

Kalantari et al.'s dataset consists of 74 samples for training and 15 samples for testing.

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: Evaluating Resilience of Vision-Based Models on Object-to-Background Compositional Changes

A real-world dataset for motion-blurred hand extraction task.

A synthetic dataset for motion-blurred hand extraction task.