TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Datasets/LaRS

LaRS

Lakes, Rivers and Seas Dataset

ImagesVideosCC-BY-NC 4.0Introduced 2023-08-18

LaRS is the largest and most diverse panoptic maritime obstacle detection dataset.

Highlights:

  • Diverse scenes from manual capture, public online videos and existing datasets
  • USV-centric point of view
  • 4000+ manually per-pixel labelled frames:
    • 3 stuff categories and 8 thing (dynamic obstacles) categories
    • 20 scene-level attributes (e.g. illumination, reflections, conditions)
  • Temporal context for each annotated frame (9 preceding frames, total: 40k frames)

Benchmarks

10-shot image generation/Q10-shot image generation/F110-shot image generation/μ10-shot image generation/mIoU10-shot image generation/PQ2D Semantic Segmentation/Q2D Semantic Segmentation/F12D Semantic Segmentation/μ2D Semantic Segmentation/mIoUPanoptic Segmentation/PQScene Parsing/QScene Parsing/F1Scene Parsing/μScene Parsing/mIoUScene Understanding/QScene Understanding/F1Scene Understanding/μScene Understanding/mIoUSemantic Segmentation/QSemantic Segmentation/F1Semantic Segmentation/μSemantic Segmentation/mIoUSemantic Segmentation/PQVideo Semantic Segmentation/QVideo Semantic Segmentation/F1Video Semantic Segmentation/μVideo Semantic Segmentation/mIoU

Statistics

Papers
5
Benchmarks
27

Links

Homepage

Tasks

10-shot image generation2D Semantic SegmentationPanoptic SegmentationScene ParsingScene UnderstandingSemantic SegmentationVideo Panoptic SegmentationVideo Semantic Segmentation