Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

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

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

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

Models/ISBNet

ISBNet

Reported on 24 benchmarks across 2 tasks · 1 paper · 8 SOTA

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

Computer Vision24 results

Instance SegmentationonS3DIS
mCov· uses extra data· 2023-03-01
74.9
SOTA
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246
Instance SegmentationonS3DIS
mPrec· uses extra data· 2023-03-01
77.5
best: 82.3 (OneFormer3D)
SOTA
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246
Instance SegmentationonS3DIS
mRec· uses extra data· 2023-03-01
77.1
SOTA
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246
Instance SegmentationonS3DIS
mWCov· uses extra data· 2023-03-01
76.8
SOTA
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246
3D Instance SegmentationonS3DIS
mCov· uses extra data· 2023-03-01
74.9
SOTA
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246
3D Instance SegmentationonS3DIS
mPrec· uses extra data· 2023-03-01
77.5
best: 82.3 (OneFormer3D)
SOTA
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246
3D Instance SegmentationonS3DIS
mRec· uses extra data· 2023-03-01
77.1
SOTA
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246
3D Instance SegmentationonS3DIS
mWCov· uses extra data· 2023-03-01
76.8
SOTA
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246
Instance SegmentationonS3DIS
AP@50· uses extra data· 2023-03-01
70.5
best: 75.8 (OneFormer3D)
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246
Instance SegmentationonS3DIS
mAP· uses extra data· 2023-03-01
60.8
best: 64.5 (Mask3D)
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246
Instance SegmentationonScanNet(v2)
mAP· 2023-03-01
55.9
best: 62.2 (Relation3D)
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246
Instance SegmentationonScanNet(v2)
mAP @ 50· 2023-03-01
76.3
best: 81.6 (Relation3D)
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246
Instance SegmentationonScanNet(v2)
mAP@25· 2023-03-01
84.5
best: 90.1 (Relation3D)
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246
Instance SegmentationonScanNet200
mAP· 2023-03-01
24.5
best: 31.5 (ODIN)
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246
Instance SegmentationonSTPLS3D
AP· 2023-03-01
49.2
best: 64.5 (EASE)
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246
Instance SegmentationonSTPLS3D
AP50· 2023-03-01
64
best: 80.8 (EASE)
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246
3D Instance SegmentationonS3DIS
AP@50· uses extra data· 2023-03-01
70.5
best: 75.8 (OneFormer3D)
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246
3D Instance SegmentationonS3DIS
mAP· uses extra data· 2023-03-01
60.8
best: 64.5 (Mask3D)
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246
3D Instance SegmentationonScanNet(v2)
mAP· 2023-03-01
55.9
best: 62.2 (Relation3D)
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246
3D Instance SegmentationonScanNet(v2)
mAP @ 50· 2023-03-01
76.3
best: 81.6 (Relation3D)
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246
3D Instance SegmentationonScanNet(v2)
mAP@25· 2023-03-01
84.5
best: 90.1 (Relation3D)
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246
3D Instance SegmentationonScanNet200
mAP· 2023-03-01
24.5
best: 31.5 (ODIN)
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246
3D Instance SegmentationonSTPLS3D
AP· 2023-03-01
49.2
best: 64.5 (EASE)
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246
3D Instance SegmentationonSTPLS3D
AP50· 2023-03-01
64
best: 80.8 (EASE)
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution arXiv:2303.00246