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/ScanNet200

ScanNet200

3D3d meshesImagesRGB-DIntroduced 2022-03-07

The ScanNet200 benchmark studies 200-class 3D semantic segmentation - an order of magnitude more class categories than previous 3D scene understanding benchmarks. The source of scene data is identical to ScanNet, but parses a larger vocabulary for semantic and instance segmentation

Benchmarks

10-shot image generation/val mIoU10-shot image generation/test mIoU3D Instance Segmentation/mAP3D Instance Segmentation/mAP@253D Instance Segmentation/mAP@503D Open-Vocabulary Instance Segmentation/mAP3D Open-Vocabulary Instance Segmentation/AP503D Open-Vocabulary Instance Segmentation/AP253D Open-Vocabulary Instance Segmentation/AP Head3D Open-Vocabulary Instance Segmentation/AP Common3D Open-Vocabulary Instance Segmentation/AP Tail3D Semantic Segmentation/val mIoU3D Semantic Segmentation/test mIoUInstance Segmentation/mAPInstance Segmentation/mAP@25Instance Segmentation/mAP@50Semantic Segmentation/val mIoUSemantic Segmentation/test mIoU

Statistics

Papers
45
Benchmarks
18

Links

Homepage

Tasks

10-shot image generation3D Instance Segmentation3D Open-Vocabulary Instance Segmentation3D Semantic SegmentationInstance SegmentationSemantic Segmentation