124 datasets found

COCO-Stuff: Thing and stuff classes in context.

A python package consisting of some well-known loss functions widely used for image segmentation.

A dataset for real-time semantic segmentation.

An urban-scale photogrammetric point cloud dataset with nearly three billion richly annotated points, covering about 7.6 km2 of the city landscape.

SemanticGAN uses a dataset of real images and their corresponding semantic segmentation masks.

DatasetGAN uses a dataset of real images and their corresponding semantic segmentation masks.

Off-road image semantic segmentation is challenging due to the presence of uneven terrains, unstructured class boundaries, irregular features and strong textures.

IDD dataset for Indian Road Scenarios contains 10K frames from 180 videos.

Object detection dataset used for training and testing the proposed alert system.

The UniSeg dataset is used for multi-dataset semantic segmentation with label shifts.

Human parsing has recently attracted a huge amount of interests and achieved great progress with the advance of deep convolutional neural networks and large-scale datasets. Most...

The SUNCG dataset is a large dataset of 3D indoor scenes with missing objects. The dataset is used to evaluate the performance of scene augmentation and context-based object...

The WeatherProof Dataset is a semantic segmentation dataset with accurate clear and adverse weather image pairs for better consistency loss in training and evaluation.

A dataset for carpet defect detection using transfer learning and semantic segmentation.

The FreDSNet dataset is a dataset for joint monocular depth estimation and semantic segmentation from single equirectangular panoramas.

A large-scale face image dataset that contains real face images and corresponding semantic segmentation map, sketch, and textual descriptions.

This paper addresses fast semantic segmentation on video. The dataset used is Cityscapes and CamVid.

A large-scale indoor dataset containing 360-degree fisheye images.

The OmniScape dataset consists of 10,000 annotated images captured from four different view angles: Front View (FV), Mirror-View Right (MVR), Mirror-View Left (MVL), and Rear...

A dataset for urban scene understanding, containing 360-degree fisheye images with annotations for various tasks.