HIDA

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision4 results

Instance SegmentationonScanNet(v2)
mAP· 2021-07-07
43.6
best: 62.2 (Relation3D)
SOTA
HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensor arXiv:2107.03180
3D Instance SegmentationonScanNet(v2)
mAP· 2021-07-07
43.6
best: 62.2 (Relation3D)
SOTA
HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensor arXiv:2107.03180
Instance SegmentationonScanNet(v2)
mAP @ 50· 2021-07-07
63.5
best: 81.6 (Relation3D)
HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensor arXiv:2107.03180
3D Instance SegmentationonScanNet(v2)
mAP @ 50· 2021-07-07
63.5
best: 81.6 (Relation3D)
HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensor arXiv:2107.03180