-
Panoptic nuScenes
Panoptic nuScenes is a multimodal dataset for lidar panoptic segmentation and tracking. -
FRNet: Frustum-Range Networks for Scalable LiDAR Segmentation
LiDAR segmentation is crucial for autonomous driving systems. The recent range-view approaches are promising for real-time processing. However, they suffer inevitably from... -
Efficient Semantic Segmentation using Gradual Grouping
Semantic segmentation is a critical computer vision component of autonomous navigation and robotic systems. It involves dense and high dimensional prediction of a label for... -
ELDA: Using Edges to Have an Edge on Semantic Segmentation Based UDA
ELDA: Using Edges to Have an Edge on Semantic Segmentation Based UDA -
KiTS19 Challenge Data
The KiTS19 Challenge Data: a collection of segmented CT imaging and treatment outcomes for 300 patients treated with partial or radical nephrectomy between 2010 and 2018. -
ScribbleKITTI
The ScribbleKITTI dataset is a dataset for weakly-supervised LiDAR semantic segmentation. It consists of a subset of the SemanticKITTI dataset with weak labels. -
AirSim-MAP
The AirSim-MAP dataset is a multi-agent perception dataset, where each agent has its own depth, pose, RGB images, and semantic segmentation masks. -
Perception-aware multi-sensor fusion for 3D LiDAR semantic segmentation
A method for LiDAR 3D point-cloud semantic segmentation exploiting perceptual information from RGB images and spatial-depth information from point clouds. -
CityPersons Dataset for Pedestrian Detection
The CityPersons dataset is a new pedestrian detection dataset, consisting of 500 images with annotated objects. -
Caltech Dataset for Pedestrian Detection
The Caltech dataset is a large-scale dataset for pedestrian detection, consisting of 4024 images with annotated objects. -
KITTI Dataset for Autonomous Driving
The KITTI dataset is a large-scale dataset for autonomous driving, consisting of 15,000 images with annotated objects. -
RandLA-Net
Semantic segmentation of large-scale point clouds. -
Uni3DL: Unified Model for 3D and Language Understanding
Uni3DL is a unified model for 3D and language understanding. It operates directly on point clouds and supports diverse 3D vision-language tasks, including semantic segmentation,... -
Prototype Refinement Network for Few-Shot Segmentation
Few-shot segmentation targets to segment new classes with few annotated images provided. It is more challenging than traditional semantic segmentation tasks that segment known... -
Context Encoding for Semantic Segmentation
Recent work has made significant progress in improving spatial resolution for pixelwise labeling with Fully Convolutional Network (FCN) framework by employing Dilated/Atrous... -
Segment Anything in Medical Images
Segment Anything in medical images. -
Segment Anything
Segment Anything (SAM) model for semantic segmentation of medical images. -
PartNet and ScanNet
Semantic segmentation and 3D detection tasks on PartNet and ScanNet datasets
