99 datasets found

Event-based visual place recognition with ensembles of temporal windows.

A high-resolution DVS dataset for lane extraction.

End-to-end event camera driving dataset: Fusing frames and events with deep learning for improved steering prediction.

End-to-end Davis driving dataset.

A large scale event-based detection dataset for automotive.

A new dataset that contains demanding illumination conditions and provides a rich set of sensory data for autonomous driving.

Nuscenes is a large-scale autonomous driving dataset that provides high-resolution BEV semantic occupancy labels for roads and vehicles.

Depth estimation, visual odometry, and bird’s-eye-view scene layout estimation present three critical tasks for driving scene perception, which is fundamental for motion...

Semantic-KITTI dataset for 3D LiDAR point cloud semantic segmentation

Novel view synthesis is a long-standing problem that revolves around rendering frames of scenes from novel camera viewpoints.

BEVFusion: Multi-task multi-sensor fusion with unified bird’s-eye view representation

The WoodScape 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...

BDD100K Dataset is a large-scale dataset for autonomous driving, containing 100,000 images, with 20,000 images for training and 80,000 images for testing.

The LISA Amazon-MLSL Vehicle Attributes (LAVA) dataset is a dataset of annotated traffic lights with various features, including color, directionality, and occlusion level.

The LAVA Salient Lights Dataset is a dataset of annotated traffic lights with a salience property, focusing on traffic lights that affect the driver’s future decisions.

The KITTI Object Detection Benchmark consists of 7,481 training images and 7,518 testing images, with 3D LiDAR point clouds and camera images.

A benchmark for stereo matching and depth estimation.

The LLAMAS dataset contains more than 100,000 high-resolution images (1276 × 717), collected primarily from highway scenarios.

The dataset used for evaluation of the proposed method. It contains images of humans and faces, with pre-annotated bounding boxes for persons and faces.

The dataset used for training the inconsistent behaviour predictor of DeepGuard.