Benchmark Results - ScanNet Benchmark

This table lists the benchmark results for the 3D semantic label scenario.

Method	avg iou	bathtub	bed	bookshelf	cabinet	chair	counter	curtain	desk	door	floor	otherfurniture	picture	refrigerator	shower curtain	sink	sofa	table	toilet	wall	window

Mix3D	0.781 1	0.964 1	0.855 1	0.843 8	0.781 1	0.858 6	0.575 2	0.831 11	0.685 4	0.714 1	0.979 1	0.594 3	0.310 13	0.801 1	0.892 4	0.841 2	0.819 3	0.723 2	0.940 4	0.887 1	0.725 8
Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann: Mix3D: Out-of-Context Data Augmentation for 3D Scenes. 3DV 2021 (Oral)
EQ-Net	0.743 8	0.620 67	0.799 11	0.849 3	0.730 7	0.822 22	0.493 18	0.897 2	0.664 7	0.681 2	0.955 11	0.562 9	0.378 1	0.760 6	0.903 1	0.738 8	0.801 9	0.673 8	0.907 14	0.877 3	0.745 1
Zetong Yang, Li Jiang, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
OccuSeg+Semantic	0.764 2	0.758 38	0.796 12	0.839 9	0.746 5	0.907 1	0.562 3	0.850 6	0.680 5	0.672 3	0.978 2	0.610 1	0.335 7	0.777 2	0.819 22	0.847 1	0.830 1	0.691 6	0.972 1	0.885 2	0.727 6

Virtual MVFusion	0.746 6	0.771 32	0.819 6	0.848 4	0.702 15	0.865 5	0.397 58	0.899 1	0.699 2	0.664 4	0.948 29	0.588 5	0.330 8	0.746 9	0.851 15	0.764 4	0.796 11	0.704 4	0.935 7	0.866 6	0.728 4
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru: Virtual Multi-view Fusion for 3D Semantic Segmentation. ECCV 2020
VMNet	0.746 6	0.870 10	0.838 2	0.858 2	0.729 8	0.850 8	0.501 13	0.874 3	0.587 30	0.658 5	0.956 8	0.564 8	0.299 16	0.765 4	0.900 2	0.716 16	0.812 6	0.631 18	0.939 5	0.858 9	0.709 10
Zeyu HU, Xuyang Bai, Jiaxiang Shang, Runze Zhang, Jiayu Dong, Xin Wang, Guangyuan Sun, Hongbo Fu, Chiew-Lan Tai: VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation. ICCV 2021 (Oral)
IPCA	0.731 10	0.890 5	0.837 3	0.864 1	0.726 9	0.873 2	0.530 7	0.824 13	0.489 61	0.647 6	0.978 2	0.609 2	0.336 6	0.624 25	0.733 34	0.758 5	0.776 19	0.570 41	0.949 2	0.877 3	0.728 4

StratifiedFormer	0.747 5	0.901 4	0.803 10	0.845 6	0.757 3	0.846 9	0.512 10	0.825 12	0.696 3	0.645 7	0.956 8	0.576 6	0.262 31	0.744 10	0.861 8	0.742 7	0.770 23	0.705 3	0.899 22	0.860 8	0.734 3
Xin Lai, Jianhui Liu, Li Jiang, Liwei Wang, Hengshuang Zhao, Shu Liu, Xiaojuan Qi, Jiaya Jia: Stratified Transformer for 3D Point Cloud Segmentation. CVPR 2022
BPNet	0.749 4	0.909 3	0.818 7	0.811 14	0.752 4	0.839 11	0.485 20	0.842 9	0.673 6	0.644 8	0.957 7	0.528 15	0.305 15	0.773 3	0.859 9	0.788 3	0.818 4	0.693 5	0.916 11	0.856 10	0.723 9
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
MinkowskiNet	0.736 9	0.859 12	0.818 7	0.832 10	0.709 12	0.840 10	0.521 9	0.853 5	0.660 9	0.643 9	0.951 19	0.544 10	0.286 22	0.731 11	0.893 3	0.675 28	0.772 21	0.683 7	0.874 42	0.852 12	0.727 6
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
O-CNN	0.762 3	0.924 2	0.823 4	0.844 7	0.770 2	0.852 7	0.577 1	0.847 7	0.711 1	0.640 10	0.958 6	0.592 4	0.217 45	0.762 5	0.888 5	0.758 5	0.813 5	0.726 1	0.932 10	0.868 5	0.744 2
Peng-Shuai Wang, Yang Liu, Yu-Xiao Guo, Chun-Yu Sun, Xin Tong: O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis. SIGGRAPH 2017
One-Thing-One-Click	0.693 19	0.743 42	0.794 14	0.655 61	0.684 18	0.822 22	0.497 16	0.719 41	0.622 17	0.617 11	0.977 4	0.447 43	0.339 5	0.750 8	0.664 49	0.703 21	0.790 15	0.596 30	0.946 3	0.855 11	0.647 25
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
PicassoNet-II	0.696 18	0.704 53	0.790 15	0.787 23	0.709 12	0.837 12	0.459 30	0.815 16	0.543 45	0.615 12	0.956 8	0.529 13	0.250 34	0.551 47	0.790 26	0.703 21	0.799 10	0.619 22	0.908 13	0.848 14	0.700 12
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
SparseConvNet	0.725 11	0.647 63	0.821 5	0.846 5	0.721 10	0.869 3	0.533 6	0.754 31	0.603 26	0.614 13	0.955 11	0.572 7	0.325 10	0.710 12	0.870 6	0.724 13	0.823 2	0.628 19	0.934 8	0.865 7	0.683 15

RFCR	0.702 15	0.889 6	0.745 35	0.813 12	0.672 20	0.818 28	0.493 18	0.815 16	0.623 16	0.610 14	0.947 32	0.470 29	0.249 36	0.594 30	0.848 16	0.705 20	0.779 18	0.646 12	0.892 28	0.823 24	0.611 35
Jingyu Gong, Jiachen Xu, Xin Tan, Haichuan Song, Yanyun Qu, Yuan Xie, Lizhuang Ma: Omni-Supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning. CVPR2021
One Thing One Click	0.701 16	0.825 19	0.796 12	0.723 37	0.716 11	0.832 15	0.433 45	0.816 14	0.634 14	0.609 15	0.969 5	0.418 55	0.344 4	0.559 44	0.833 19	0.715 17	0.808 7	0.560 45	0.902 19	0.847 15	0.680 16

INS-Conv-semantic	0.717 13	0.751 41	0.759 26	0.812 13	0.704 14	0.868 4	0.537 5	0.842 9	0.609 22	0.608 16	0.953 15	0.534 11	0.293 18	0.616 26	0.864 7	0.719 15	0.793 13	0.640 13	0.933 9	0.845 17	0.663 19

JSENet	0.699 17	0.881 9	0.762 24	0.821 11	0.667 21	0.800 42	0.522 8	0.792 23	0.613 18	0.607 17	0.935 57	0.492 22	0.205 50	0.576 36	0.853 12	0.691 23	0.758 29	0.652 11	0.872 45	0.828 21	0.649 24
Zeyu HU, Mingmin Zhen, Xuyang BAI, Hongbo Fu, Chiew-lan Tai: JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds. ECCV 2020
Feature-Geometry Net	0.690 21	0.884 7	0.754 30	0.795 21	0.647 26	0.818 28	0.422 47	0.802 21	0.612 19	0.604 18	0.945 38	0.462 32	0.189 57	0.563 42	0.853 12	0.726 10	0.765 24	0.632 16	0.904 16	0.821 26	0.606 39
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
Feature_GeometricNet	0.690 21	0.884 7	0.754 30	0.795 21	0.647 26	0.818 28	0.422 47	0.802 21	0.612 19	0.604 18	0.945 38	0.462 32	0.189 57	0.563 42	0.853 12	0.726 10	0.765 24	0.632 16	0.904 16	0.821 26	0.606 39
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
MatchingNet	0.724 12	0.812 22	0.812 9	0.810 15	0.735 6	0.834 14	0.495 17	0.860 4	0.572 35	0.602 20	0.954 13	0.512 18	0.280 23	0.757 7	0.845 18	0.725 12	0.780 17	0.606 27	0.937 6	0.851 13	0.700 12

Superpoint Network	0.683 26	0.851 14	0.728 44	0.800 20	0.653 24	0.806 38	0.468 25	0.804 19	0.572 35	0.602 20	0.946 35	0.453 39	0.239 39	0.519 53	0.822 20	0.689 26	0.762 27	0.595 32	0.895 25	0.827 22	0.630 31

KP-FCNN	0.684 24	0.847 15	0.758 28	0.784 25	0.647 26	0.814 32	0.473 22	0.772 26	0.605 24	0.594 22	0.935 57	0.450 41	0.181 61	0.587 31	0.805 24	0.690 24	0.785 16	0.614 23	0.882 34	0.819 28	0.632 30
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
CU-Hybrid Net	0.693 19	0.596 71	0.789 16	0.803 18	0.677 19	0.800 42	0.469 24	0.846 8	0.554 43	0.591 23	0.948 29	0.500 20	0.316 12	0.609 27	0.847 17	0.732 9	0.808 7	0.593 33	0.894 26	0.839 18	0.652 22

contrastBoundary	0.705 14	0.769 35	0.775 20	0.809 16	0.687 17	0.820 25	0.439 43	0.812 18	0.661 8	0.591 23	0.945 38	0.515 17	0.171 63	0.633 22	0.856 10	0.720 14	0.796 11	0.668 9	0.889 30	0.847 15	0.689 14
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
VACNN++	0.684 24	0.728 48	0.757 29	0.776 27	0.690 16	0.804 40	0.464 28	0.816 14	0.577 34	0.587 25	0.945 38	0.508 19	0.276 25	0.671 13	0.710 39	0.663 33	0.750 32	0.589 35	0.881 36	0.832 20	0.653 21

ROSMRF3D	0.673 29	0.789 25	0.748 33	0.763 32	0.635 32	0.814 32	0.407 54	0.747 33	0.581 33	0.573 26	0.950 23	0.484 23	0.271 27	0.607 28	0.754 30	0.649 39	0.774 20	0.596 30	0.883 33	0.823 24	0.606 39

Supervoxel-CNN	0.635 45	0.656 61	0.711 46	0.719 39	0.613 36	0.757 64	0.444 40	0.765 28	0.534 47	0.566 27	0.928 65	0.478 26	0.272 26	0.636 19	0.531 59	0.664 32	0.645 65	0.508 64	0.864 50	0.792 47	0.611 35

joint point-based	0.634 46	0.614 68	0.778 19	0.667 57	0.633 33	0.825 20	0.420 49	0.804 19	0.467 66	0.561 28	0.951 19	0.494 21	0.291 19	0.566 40	0.458 65	0.579 62	0.764 26	0.559 47	0.838 56	0.814 29	0.598 44
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
VI-PointConv	0.676 28	0.770 34	0.754 30	0.783 26	0.621 34	0.814 32	0.552 4	0.758 29	0.571 37	0.557 29	0.954 13	0.529 13	0.268 30	0.530 51	0.682 44	0.675 28	0.719 40	0.603 28	0.888 31	0.833 19	0.665 18
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
MVPNet	0.641 37	0.831 16	0.715 45	0.671 55	0.590 43	0.781 52	0.394 59	0.679 51	0.642 11	0.553 30	0.937 55	0.462 32	0.256 32	0.649 17	0.406 71	0.626 48	0.691 53	0.666 10	0.877 38	0.792 47	0.608 38
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
FusionNet	0.688 23	0.704 53	0.741 39	0.754 34	0.656 22	0.829 17	0.501 13	0.741 36	0.609 22	0.548 31	0.950 23	0.522 16	0.371 2	0.633 22	0.756 29	0.715 17	0.771 22	0.623 20	0.861 51	0.814 29	0.658 20
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
SALANet	0.670 30	0.816 21	0.770 22	0.768 30	0.652 25	0.807 37	0.451 32	0.747 33	0.659 10	0.545 32	0.924 67	0.473 28	0.149 73	0.571 38	0.811 23	0.635 47	0.746 33	0.623 20	0.892 28	0.794 42	0.570 52

PointContrast_LA_SEM	0.683 26	0.757 39	0.784 17	0.786 24	0.639 30	0.824 21	0.408 52	0.775 25	0.604 25	0.541 33	0.934 61	0.532 12	0.269 28	0.552 45	0.777 27	0.645 44	0.793 13	0.640 13	0.913 12	0.824 23	0.671 17

PointASNL	0.666 31	0.703 55	0.781 18	0.751 36	0.655 23	0.830 16	0.471 23	0.769 27	0.474 64	0.537 34	0.951 19	0.475 27	0.279 24	0.635 20	0.698 43	0.675 28	0.751 31	0.553 50	0.816 62	0.806 33	0.703 11
Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui: PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling. CVPR 2020
PD-Net	0.638 41	0.797 24	0.769 23	0.641 67	0.590 43	0.820 25	0.461 29	0.537 72	0.637 13	0.536 35	0.947 32	0.388 62	0.206 49	0.656 15	0.668 47	0.647 42	0.732 38	0.585 37	0.868 48	0.793 44	0.473 74

SAFNet-seg	0.654 35	0.752 40	0.734 41	0.664 58	0.583 47	0.815 31	0.399 57	0.754 31	0.639 12	0.535 36	0.942 47	0.470 29	0.309 14	0.665 14	0.539 57	0.650 38	0.708 46	0.635 15	0.857 53	0.793 44	0.642 26
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
PPCNN++	0.636 43	0.724 49	0.697 53	0.672 52	0.636 31	0.775 56	0.403 56	0.582 67	0.588 29	0.533 37	0.949 25	0.453 39	0.218 44	0.571 38	0.676 45	0.663 33	0.635 70	0.580 39	0.906 15	0.808 32	0.650 23
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, Junmo Kim: Projection-based Point Convolution for Efficient Point Cloud Segmentation. IEEE Access
SConv	0.636 43	0.830 17	0.697 53	0.752 35	0.572 52	0.780 54	0.445 37	0.716 42	0.529 48	0.530 38	0.951 19	0.446 44	0.170 64	0.507 57	0.666 48	0.636 46	0.682 55	0.541 57	0.886 32	0.799 36	0.594 46

FusionAwareConv	0.630 52	0.604 70	0.741 39	0.766 31	0.590 43	0.747 66	0.501 13	0.734 38	0.503 55	0.527 39	0.919 71	0.454 37	0.323 11	0.550 48	0.420 70	0.678 27	0.688 54	0.544 53	0.896 24	0.795 40	0.627 32
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
HPEIN	0.618 56	0.729 47	0.668 64	0.647 64	0.597 41	0.766 60	0.414 50	0.680 50	0.520 50	0.525 40	0.946 35	0.432 46	0.215 46	0.493 60	0.599 54	0.638 45	0.617 71	0.570 41	0.897 23	0.806 33	0.605 42
Li Jiang, Hengshuang Zhao, Shu Liu, Xiaoyong Shen, Chi-Wing Fu, Jiaya Jia: Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation. ICCV 2019
DCM-Net	0.658 33	0.778 28	0.702 49	0.806 17	0.619 35	0.813 35	0.468 25	0.693 48	0.494 57	0.524 41	0.941 49	0.449 42	0.298 17	0.510 55	0.821 21	0.675 28	0.727 39	0.568 43	0.826 59	0.803 35	0.637 28
Jonas Schult, Francis Engelmann, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
FPConv	0.639 40	0.785 26	0.760 25	0.713 42	0.603 38	0.798 45	0.392 60	0.534 73	0.603 26	0.524 41	0.948 29	0.457 35	0.250 34	0.538 49	0.723 37	0.598 57	0.696 51	0.614 23	0.872 45	0.799 36	0.567 54
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
RandLA-Net	0.645 36	0.778 28	0.731 42	0.699 44	0.577 48	0.829 17	0.446 35	0.736 37	0.477 63	0.523 43	0.945 38	0.454 37	0.269 28	0.484 62	0.749 33	0.618 51	0.738 34	0.599 29	0.827 58	0.792 47	0.621 33

DenSeR	0.628 53	0.800 23	0.625 74	0.719 39	0.545 58	0.806 38	0.445 37	0.597 62	0.448 70	0.519 44	0.938 54	0.481 24	0.328 9	0.489 61	0.499 64	0.657 37	0.759 28	0.592 34	0.881 36	0.797 39	0.634 29

SIConv	0.625 55	0.830 17	0.694 56	0.757 33	0.563 54	0.772 59	0.448 34	0.647 57	0.520 50	0.509 45	0.949 25	0.431 47	0.191 56	0.496 59	0.614 53	0.647 42	0.672 59	0.535 60	0.876 39	0.783 52	0.571 51

SegGroup_sem	0.627 54	0.818 20	0.747 34	0.701 43	0.602 39	0.764 61	0.385 65	0.629 59	0.490 59	0.508 46	0.931 64	0.409 57	0.201 53	0.564 41	0.725 36	0.618 51	0.692 52	0.539 58	0.873 43	0.794 42	0.548 61
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation.
APCF-Net	0.631 49	0.742 43	0.687 63	0.672 52	0.557 56	0.792 49	0.408 52	0.665 54	0.545 44	0.508 46	0.952 18	0.428 49	0.186 59	0.634 21	0.702 41	0.620 49	0.706 47	0.555 49	0.873 43	0.798 38	0.581 48
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
SPH3D-GCN	0.610 57	0.858 13	0.772 21	0.489 79	0.532 59	0.792 49	0.404 55	0.643 58	0.570 38	0.507 48	0.935 57	0.414 56	0.046 83	0.510 55	0.702 41	0.602 55	0.705 48	0.549 52	0.859 52	0.773 57	0.534 63
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
PointConv	0.666 31	0.781 27	0.759 26	0.699 44	0.644 29	0.822 22	0.475 21	0.779 24	0.564 40	0.504 49	0.953 15	0.428 49	0.203 52	0.586 33	0.754 30	0.661 35	0.753 30	0.588 36	0.902 19	0.813 31	0.642 26
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PointMTL	0.632 48	0.731 46	0.688 61	0.675 51	0.591 42	0.784 51	0.444 40	0.565 69	0.610 21	0.492 50	0.949 25	0.456 36	0.254 33	0.587 31	0.706 40	0.599 56	0.665 61	0.612 26	0.868 48	0.791 50	0.579 49

MCCNN	0.633 47	0.866 11	0.731 42	0.771 28	0.576 49	0.809 36	0.410 51	0.684 49	0.497 56	0.491 51	0.949 25	0.466 31	0.105 77	0.581 34	0.646 51	0.620 49	0.680 56	0.542 56	0.817 61	0.795 40	0.618 34
P. Hermosilla, T. Ritschel, P.P. Vazquez, A. Vinacua, T. Ropinski: Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Clouds. SIGGRAPH Asia 2018
3DSM_DMMF	0.631 49	0.626 66	0.745 35	0.801 19	0.607 37	0.751 65	0.506 11	0.729 40	0.565 39	0.491 51	0.866 80	0.434 45	0.197 55	0.595 29	0.630 52	0.709 19	0.705 48	0.560 45	0.875 40	0.740 66	0.491 69

PointConv-SFPN	0.641 37	0.776 30	0.703 48	0.721 38	0.557 56	0.826 19	0.451 32	0.672 53	0.563 41	0.483 53	0.943 46	0.425 52	0.162 68	0.644 18	0.726 35	0.659 36	0.709 45	0.572 40	0.875 40	0.786 51	0.559 57

HPGCNN	0.656 34	0.698 56	0.743 37	0.650 62	0.564 53	0.820 25	0.505 12	0.758 29	0.631 15	0.479 54	0.945 38	0.480 25	0.226 40	0.572 37	0.774 28	0.690 24	0.735 36	0.614 23	0.853 54	0.776 56	0.597 45
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
CCRFNet	0.589 62	0.766 36	0.659 68	0.683 49	0.470 68	0.740 68	0.387 64	0.620 61	0.490 59	0.476 55	0.922 69	0.355 69	0.245 37	0.511 54	0.511 62	0.571 63	0.643 66	0.493 68	0.872 45	0.762 60	0.600 43

DVVNet	0.562 66	0.648 62	0.700 51	0.770 29	0.586 46	0.687 73	0.333 71	0.650 55	0.514 53	0.475 56	0.906 75	0.359 67	0.223 42	0.340 74	0.442 69	0.422 78	0.668 60	0.501 65	0.708 73	0.779 53	0.534 63

ROSMRF	0.580 63	0.772 31	0.707 47	0.681 50	0.563 54	0.764 61	0.362 67	0.515 74	0.465 67	0.465 57	0.936 56	0.427 51	0.207 48	0.438 65	0.577 55	0.536 67	0.675 58	0.486 69	0.723 72	0.779 53	0.524 65

PointMRNet	0.640 39	0.717 52	0.701 50	0.692 47	0.576 49	0.801 41	0.467 27	0.716 42	0.563 41	0.459 58	0.953 15	0.429 48	0.169 65	0.581 34	0.854 11	0.605 53	0.710 43	0.550 51	0.894 26	0.793 44	0.575 50

3DMV, FTSDF	0.501 73	0.558 75	0.608 77	0.424 83	0.478 66	0.690 72	0.246 79	0.586 65	0.468 65	0.450 59	0.911 73	0.394 60	0.160 69	0.438 65	0.212 80	0.432 77	0.541 78	0.475 71	0.742 70	0.727 68	0.477 72

wsss-transformer	0.600 59	0.634 64	0.743 37	0.697 46	0.601 40	0.781 52	0.437 44	0.585 66	0.493 58	0.446 60	0.933 62	0.394 60	0.011 85	0.654 16	0.661 50	0.603 54	0.733 37	0.526 61	0.832 57	0.761 61	0.480 71

PointNet2-SFPN	0.631 49	0.771 32	0.692 58	0.672 52	0.524 60	0.837 12	0.440 42	0.706 46	0.538 46	0.446 60	0.944 44	0.421 54	0.219 43	0.552 45	0.751 32	0.591 59	0.737 35	0.543 55	0.901 21	0.768 58	0.557 58

LAP-D	0.594 60	0.720 50	0.692 58	0.637 68	0.456 69	0.773 58	0.391 62	0.730 39	0.587 30	0.445 62	0.940 51	0.381 63	0.288 20	0.434 67	0.453 67	0.591 59	0.649 63	0.581 38	0.777 66	0.749 65	0.610 37

DPC	0.592 61	0.720 50	0.700 51	0.602 72	0.480 65	0.762 63	0.380 66	0.713 44	0.585 32	0.437 63	0.940 51	0.369 65	0.288 20	0.434 67	0.509 63	0.590 61	0.639 68	0.567 44	0.772 67	0.755 63	0.592 47
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
PointSPNet	0.637 42	0.734 45	0.692 58	0.714 41	0.576 49	0.797 46	0.446 35	0.743 35	0.598 28	0.437 63	0.942 47	0.403 58	0.150 72	0.626 24	0.800 25	0.649 39	0.697 50	0.557 48	0.846 55	0.777 55	0.563 55

AttAN	0.609 58	0.760 37	0.667 65	0.649 63	0.521 61	0.793 47	0.457 31	0.648 56	0.528 49	0.434 65	0.947 32	0.401 59	0.153 71	0.454 64	0.721 38	0.648 41	0.717 41	0.536 59	0.904 16	0.765 59	0.485 70
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
Online SegFusion	0.515 72	0.607 69	0.644 72	0.579 74	0.434 71	0.630 79	0.353 68	0.628 60	0.440 71	0.410 66	0.762 84	0.307 74	0.167 66	0.520 52	0.403 72	0.516 68	0.565 73	0.447 76	0.678 76	0.701 72	0.514 67
Davide Menini, Suryansh Kumar, Martin R. Oswald, Erik Sandstroem, Cristian Sminchisescu, Luc van Gool: A Real-Time Learning Framework for Joint 3D Reconstruction and Semantic Segmentation. Robotics and Automation Letters Submission
3DWSSS	0.425 81	0.525 77	0.647 70	0.522 77	0.324 81	0.488 85	0.077 86	0.712 45	0.353 80	0.401 67	0.636 86	0.281 78	0.176 62	0.340 74	0.565 56	0.175 86	0.551 76	0.398 81	0.370 86	0.602 81	0.361 79

TextureNet	0.566 65	0.672 60	0.664 66	0.671 55	0.494 63	0.719 69	0.445 37	0.678 52	0.411 76	0.396 68	0.935 57	0.356 68	0.225 41	0.412 69	0.535 58	0.565 64	0.636 69	0.464 72	0.794 65	0.680 75	0.568 53
Jingwei Huang, Haotian Zhang, Li Yi, Thomas Funkerhouser, Matthias Niessner, Leonidas Guibas: TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes. CVPR
3DMV	0.484 75	0.484 81	0.538 81	0.643 66	0.424 73	0.606 82	0.310 72	0.574 68	0.433 74	0.378 69	0.796 82	0.301 75	0.214 47	0.537 50	0.208 81	0.472 75	0.507 82	0.413 80	0.693 74	0.602 81	0.539 62
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
SQN_0.1%	0.569 64	0.676 58	0.696 55	0.657 60	0.497 62	0.779 55	0.424 46	0.548 70	0.515 52	0.376 70	0.902 78	0.422 53	0.357 3	0.379 71	0.456 66	0.596 58	0.659 62	0.544 53	0.685 75	0.665 78	0.556 59

Pointnet++ & Feature	0.557 67	0.735 44	0.661 67	0.686 48	0.491 64	0.744 67	0.392 60	0.539 71	0.451 69	0.375 71	0.946 35	0.376 64	0.205 50	0.403 70	0.356 74	0.553 66	0.643 66	0.497 66	0.824 60	0.756 62	0.515 66

PointMRNet-lite	0.553 68	0.633 65	0.648 69	0.659 59	0.430 72	0.800 42	0.390 63	0.592 64	0.454 68	0.371 72	0.939 53	0.368 66	0.136 75	0.368 72	0.448 68	0.560 65	0.715 42	0.486 69	0.882 34	0.720 70	0.462 75

GMLPs	0.538 69	0.495 79	0.693 57	0.647 64	0.471 67	0.793 47	0.300 73	0.477 75	0.505 54	0.358 73	0.903 77	0.327 72	0.081 80	0.472 63	0.529 60	0.448 76	0.710 43	0.509 62	0.746 69	0.737 67	0.554 60

subcloud_weak	0.516 71	0.676 58	0.591 79	0.609 69	0.442 70	0.774 57	0.335 70	0.597 62	0.422 75	0.357 74	0.932 63	0.341 71	0.094 79	0.298 76	0.528 61	0.473 74	0.676 57	0.495 67	0.602 80	0.721 69	0.349 81

PCNN	0.498 74	0.559 74	0.644 72	0.560 76	0.420 74	0.711 71	0.229 81	0.414 76	0.436 72	0.352 75	0.941 49	0.324 73	0.155 70	0.238 80	0.387 73	0.493 70	0.529 79	0.509 62	0.813 63	0.751 64	0.504 68

PointCNN with RGB	0.458 76	0.577 73	0.611 76	0.356 85	0.321 82	0.715 70	0.299 75	0.376 79	0.328 82	0.319 76	0.944 44	0.285 77	0.164 67	0.216 83	0.229 79	0.484 72	0.545 77	0.456 74	0.755 68	0.709 71	0.475 73
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
PNET2	0.442 78	0.548 76	0.548 80	0.597 73	0.363 78	0.628 80	0.300 73	0.292 80	0.374 78	0.307 77	0.881 79	0.268 79	0.186 59	0.238 80	0.204 82	0.407 79	0.506 83	0.449 75	0.667 77	0.620 80	0.462 75

PanopticFusion-label	0.529 70	0.491 80	0.688 61	0.604 71	0.386 75	0.632 78	0.225 83	0.705 47	0.434 73	0.293 78	0.815 81	0.348 70	0.241 38	0.499 58	0.669 46	0.507 69	0.649 63	0.442 77	0.796 64	0.602 81	0.561 56
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
Tangent Convolutions	0.438 80	0.437 83	0.646 71	0.474 80	0.369 77	0.645 77	0.353 68	0.258 82	0.282 84	0.279 79	0.918 72	0.298 76	0.147 74	0.283 77	0.294 76	0.487 71	0.562 74	0.427 79	0.619 79	0.633 79	0.352 80
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
SurfaceConvPF	0.442 78	0.505 78	0.622 75	0.380 84	0.342 80	0.654 76	0.227 82	0.397 78	0.367 79	0.276 80	0.924 67	0.240 81	0.198 54	0.359 73	0.262 77	0.366 80	0.581 72	0.435 78	0.640 78	0.668 76	0.398 77
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
ScanNet+FTSDF	0.383 83	0.297 85	0.491 83	0.432 82	0.358 79	0.612 81	0.274 77	0.116 84	0.411 76	0.265 81	0.904 76	0.229 82	0.079 81	0.250 78	0.185 83	0.320 83	0.510 80	0.385 82	0.548 82	0.597 84	0.394 78

PointNet++	0.339 84	0.584 72	0.478 84	0.458 81	0.256 85	0.360 86	0.250 78	0.247 83	0.278 85	0.261 82	0.677 85	0.183 84	0.117 76	0.212 84	0.145 85	0.364 81	0.346 86	0.232 86	0.548 82	0.523 85	0.252 84
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
FCPN	0.447 77	0.679 57	0.604 78	0.578 75	0.380 76	0.682 74	0.291 76	0.106 85	0.483 62	0.258 83	0.920 70	0.258 80	0.025 84	0.231 82	0.325 75	0.480 73	0.560 75	0.463 73	0.725 71	0.666 77	0.231 85
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
SPLAT Net	0.393 82	0.472 82	0.511 82	0.606 70	0.311 83	0.656 75	0.245 80	0.405 77	0.328 82	0.197 84	0.927 66	0.227 83	0.000 87	0.001 87	0.249 78	0.271 85	0.510 80	0.383 83	0.593 81	0.699 73	0.267 83
Hang Su, Varun Jampani, Deqing Sun, Subhransu Maji, Evangelos Kalogerakis, Ming-Hsuan Yang, Jan Kautz: SPLATNet: Sparse Lattice Networks for Point Cloud Processing. CVPR 2018
ScanNet	0.306 86	0.203 86	0.366 85	0.501 78	0.311 83	0.524 84	0.211 84	0.002 87	0.342 81	0.189 85	0.786 83	0.145 86	0.102 78	0.245 79	0.152 84	0.318 84	0.348 85	0.300 85	0.460 85	0.437 86	0.182 86
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
SSC-UNet	0.308 85	0.353 84	0.290 86	0.278 86	0.166 86	0.553 83	0.169 85	0.286 81	0.147 86	0.148 86	0.908 74	0.182 85	0.064 82	0.023 86	0.018 87	0.354 82	0.363 84	0.345 84	0.546 84	0.685 74	0.278 82

ERROR	0.054 87	0.000 87	0.041 87	0.172 87	0.030 87	0.062 87	0.001 87	0.035 86	0.004 87	0.051 87	0.143 87	0.019 87	0.003 86	0.041 85	0.050 86	0.003 87	0.054 87	0.018 87	0.005 87	0.264 87	0.082 87

This table lists the benchmark results for the 3D semantic instance scenario.

Method	avg ap 50%	bathtub	bed	bookshelf	cabinet	chair	counter	curtain	desk	door	otherfurniture	picture	refrigerator	shower curtain	sink	sofa	table	toilet	window

DKNet	0.718 5	1.000 1	0.814 8	0.782 9	0.619 6	0.872 2	0.224 9	0.751 12	0.569 8	0.677 1	0.585 8	0.724 1	0.633 14	0.981 18	0.515 20	0.819 6	0.736 5	1.000 1	0.617 2

SoftGroup	0.761 2	1.000 1	0.808 11	0.845 5	0.716 1	0.862 5	0.243 8	0.824 3	0.655 4	0.620 2	0.734 2	0.699 5	0.791 3	0.981 18	0.716 4	0.844 4	0.769 3	1.000 1	0.594 5
Thang Vu, Kookhoi Kim, Tung M. Luu, Xuan Thanh Nguyen, Chang D. Yoo: SoftGroup for 3D Instance Segmentaiton on Point Clouds. CVPR 2022 [Oral]
GraphCut	0.732 3	1.000 1	0.788 16	0.724 15	0.642 5	0.859 6	0.248 7	0.787 8	0.618 6	0.596 3	0.653 3	0.722 2	0.583 21	1.000 1	0.766 2	0.861 2	0.825 1	1.000 1	0.504 13

SoftGroup++	0.769 1	1.000 1	0.803 13	0.937 1	0.684 3	0.865 3	0.213 11	0.870 2	0.664 2	0.571 4	0.758 1	0.702 4	0.807 1	1.000 1	0.653 11	0.902 1	0.792 2	1.000 1	0.626 1

OccuSeg+instance	0.672 10	1.000 1	0.758 24	0.682 17	0.576 12	0.842 7	0.477 1	0.504 29	0.524 9	0.567 5	0.585 10	0.451 13	0.557 22	1.000 1	0.751 3	0.797 8	0.563 22	1.000 1	0.467 20
Lei Han, Tian Zheng, Lan Xu, Lu Fang: OccuSeg: Occupancy-aware 3D Instance Segmentation. CVPR2020
MaskVoteNet_Coarse	0.677 9	1.000 1	0.847 4	0.771 10	0.509 20	0.816 9	0.277 5	0.558 26	0.482 10	0.562 6	0.640 4	0.448 14	0.700 4	1.000 1	0.666 6	0.852 3	0.578 19	0.997 19	0.488 17

SSTNet	0.698 7	1.000 1	0.697 30	0.888 3	0.556 14	0.803 14	0.387 2	0.626 19	0.417 17	0.556 7	0.585 9	0.702 3	0.600 16	1.000 1	0.824 1	0.720 21	0.692 7	1.000 1	0.509 12
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia: Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. ICCV2021
SphereSeg	0.680 8	1.000 1	0.856 2	0.744 14	0.618 7	0.893 1	0.151 13	0.651 17	0.713 1	0.537 8	0.579 11	0.430 18	0.651 6	1.000 1	0.389 29	0.744 17	0.697 6	0.991 24	0.601 4

HAIS	0.699 6	1.000 1	0.849 3	0.820 6	0.675 4	0.808 13	0.279 4	0.757 11	0.465 13	0.517 9	0.596 6	0.559 8	0.600 16	1.000 1	0.654 10	0.767 10	0.676 9	0.994 23	0.560 9
Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang: Hierarchical Aggregation for 3D Instance Segmentation. ICCV 2021
IPCA-Inst	0.731 4	1.000 1	0.788 17	0.884 4	0.698 2	0.788 19	0.252 6	0.760 10	0.646 5	0.511 10	0.637 5	0.665 6	0.804 2	1.000 1	0.644 12	0.778 9	0.747 4	1.000 1	0.561 8

PCJC	0.578 22	1.000 1	0.810 10	0.583 26	0.449 26	0.813 12	0.042 29	0.603 22	0.341 23	0.490 11	0.465 21	0.410 20	0.650 7	0.835 28	0.264 34	0.694 25	0.561 23	0.889 32	0.504 14

DD-UNet+Group	0.635 19	0.667 29	0.797 15	0.714 16	0.562 13	0.774 21	0.146 14	0.810 6	0.429 16	0.476 12	0.546 16	0.399 21	0.633 14	1.000 1	0.632 13	0.722 20	0.609 15	1.000 1	0.514 10
H. Liu, R. Liu, K. Yang, J. Zhang, K. Peng, R. Stiefelhagen: HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensor. ICCVW 2021
INS-Conv-instance	0.657 12	1.000 1	0.760 22	0.667 19	0.581 10	0.863 4	0.323 3	0.655 16	0.477 11	0.473 13	0.549 14	0.432 17	0.650 7	1.000 1	0.655 9	0.738 18	0.585 18	0.944 28	0.472 19

SSEN	0.575 23	1.000 1	0.761 21	0.473 29	0.477 24	0.795 17	0.066 25	0.529 27	0.658 3	0.460 14	0.461 22	0.380 23	0.331 34	0.859 21	0.401 28	0.692 26	0.653 11	1.000 1	0.348 28
Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim: Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning. Arxiv
Mask-Group	0.664 11	1.000 1	0.822 7	0.764 13	0.616 8	0.815 10	0.139 17	0.694 15	0.597 7	0.459 15	0.566 12	0.599 7	0.600 16	0.516 35	0.715 5	0.819 7	0.635 13	1.000 1	0.603 3
Min Zhong, Xinghao Chen, Xiaokang Chen, Gang Zeng, Yunhe Wang: MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation. ICME 2022
GICN	0.638 17	1.000 1	0.895 1	0.800 7	0.480 23	0.676 24	0.144 15	0.737 13	0.354 21	0.447 16	0.400 27	0.365 24	0.700 4	1.000 1	0.569 16	0.836 5	0.599 16	1.000 1	0.473 18

PointGroup	0.636 18	1.000 1	0.765 20	0.624 21	0.505 22	0.797 16	0.116 20	0.696 14	0.384 19	0.441 17	0.559 13	0.476 11	0.596 19	1.000 1	0.666 6	0.756 14	0.556 26	0.997 19	0.513 11
Li Jiang, Hengshuang Zhao, Shaoshuai Shi, Shu Liu, Chi-Wing Fu, Jiaya Jia: PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation. CVPR 2020 [oral]
Dyco3D	0.641 16	1.000 1	0.841 5	0.893 2	0.531 17	0.802 15	0.115 21	0.588 24	0.448 14	0.438 18	0.537 17	0.430 19	0.550 23	0.857 22	0.534 18	0.764 12	0.657 10	0.987 25	0.568 6
Tong He; Chunhua Shen; Anton van den Hengel: DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. CVPR2021
3D-MPA	0.611 21	1.000 1	0.833 6	0.765 12	0.526 18	0.756 22	0.136 19	0.588 24	0.470 12	0.438 19	0.432 25	0.358 25	0.650 7	0.857 22	0.429 25	0.765 11	0.557 25	1.000 1	0.430 22
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner: 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. CVPR 2020
RPGN	0.643 15	1.000 1	0.758 23	0.582 27	0.539 15	0.826 8	0.046 28	0.765 9	0.372 20	0.436 20	0.588 7	0.539 10	0.650 7	1.000 1	0.577 15	0.750 15	0.653 12	0.997 19	0.495 16

PE	0.645 14	1.000 1	0.773 19	0.798 8	0.538 16	0.786 20	0.088 24	0.799 7	0.350 22	0.435 21	0.547 15	0.545 9	0.646 13	0.933 20	0.562 17	0.761 13	0.556 27	0.997 19	0.501 15
Biao Zhang, Peter Wonka: Point Cloud Instance Segmentation using Probabilistic Embeddings. CVPR 2021
CSC-Pretrained	0.648 13	1.000 1	0.810 9	0.768 11	0.523 19	0.813 11	0.143 16	0.819 4	0.389 18	0.422 22	0.511 18	0.443 15	0.650 7	1.000 1	0.624 14	0.732 19	0.634 14	1.000 1	0.375 26

MTML	0.549 25	1.000 1	0.807 12	0.588 25	0.327 30	0.647 26	0.004 34	0.815 5	0.180 30	0.418 23	0.364 30	0.182 29	0.445 28	1.000 1	0.442 24	0.688 27	0.571 21	1.000 1	0.396 24
Jean Lahoud, Bernard Ghanem, Marc Pollefeys, Martin R. Oswald: 3D Instance Segmentation via Multi-task Metric Learning. ICCV 2019 [oral]
SALoss-ResNet	0.459 31	1.000 1	0.737 25	0.159 41	0.259 33	0.587 31	0.138 18	0.475 31	0.217 29	0.416 24	0.408 26	0.128 32	0.315 35	0.714 30	0.411 26	0.536 36	0.590 17	0.873 35	0.304 30
Zhidong Liang, Ming Yang, Hao Li, Chunxiang Wang: 3D Instance Embedding Learning With a Structure-Aware Loss Function for Point Cloud Segmentation. IEEE Robotics and Automation Letters (IROS2020)
Sparse R-CNN	0.515 26	1.000 1	0.538 37	0.282 32	0.468 25	0.790 18	0.173 12	0.345 33	0.429 15	0.413 25	0.484 20	0.176 30	0.595 20	0.591 33	0.522 19	0.668 28	0.476 31	0.986 26	0.327 29

DENet	0.629 20	1.000 1	0.797 14	0.608 22	0.589 9	0.627 28	0.219 10	0.882 1	0.310 24	0.402 26	0.383 29	0.396 22	0.650 7	1.000 1	0.663 8	0.543 35	0.691 8	1.000 1	0.568 7

RWSeg	0.567 24	0.528 37	0.708 29	0.626 20	0.580 11	0.745 23	0.063 26	0.627 18	0.240 28	0.400 27	0.497 19	0.464 12	0.515 24	1.000 1	0.475 22	0.745 16	0.571 20	1.000 1	0.429 23

SegGroup_ins	0.445 33	0.667 29	0.773 18	0.185 38	0.317 31	0.656 25	0.000 37	0.407 32	0.134 33	0.381 28	0.267 33	0.217 28	0.476 26	0.714 30	0.452 23	0.629 30	0.514 29	1.000 1	0.222 35
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation.
MASC	0.447 32	0.528 37	0.555 35	0.381 30	0.382 27	0.633 27	0.002 35	0.509 28	0.260 26	0.361 29	0.432 24	0.327 26	0.451 27	0.571 34	0.367 31	0.639 29	0.386 32	0.980 27	0.276 32
Chen Liu, Yasutaka Furukawa: MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation.
Occipital-SCS	0.512 27	1.000 1	0.716 26	0.509 28	0.506 21	0.611 29	0.092 23	0.602 23	0.177 31	0.346 30	0.383 28	0.165 31	0.442 29	0.850 27	0.386 30	0.618 31	0.543 28	0.889 32	0.389 25

3D-BoNet	0.488 28	1.000 1	0.672 32	0.590 24	0.301 32	0.484 38	0.098 22	0.620 20	0.306 25	0.341 31	0.259 34	0.125 33	0.434 31	0.796 29	0.402 27	0.499 37	0.513 30	0.909 31	0.439 21
Bo Yang, Jianan Wang, Ronald Clark, Qingyong Hu, Sen Wang, Andrew Markham, Niki Trigoni: Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds. NeurIPS 2019 Spotlight
3D-SIS	0.382 34	1.000 1	0.432 39	0.245 34	0.190 35	0.577 32	0.013 32	0.263 35	0.033 39	0.320 32	0.240 35	0.075 35	0.422 32	0.857 22	0.117 37	0.699 23	0.271 39	0.883 34	0.235 34
Ji Hou, Angela Dai, Matthias Niessner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. CVPR 2019
SPG_WSIS	0.470 30	0.667 29	0.685 31	0.677 18	0.372 28	0.562 33	0.000 37	0.482 30	0.244 27	0.316 33	0.298 31	0.052 39	0.442 30	0.857 22	0.267 33	0.702 22	0.559 24	1.000 1	0.287 31

R-PointNet	0.306 37	0.500 39	0.405 40	0.311 31	0.348 29	0.589 30	0.054 27	0.068 41	0.126 34	0.283 34	0.290 32	0.028 40	0.219 38	0.214 39	0.331 32	0.396 41	0.275 37	0.821 37	0.245 33

Hier3D	0.323 35	0.667 29	0.542 36	0.264 33	0.157 38	0.550 34	0.000 37	0.205 38	0.009 40	0.270 35	0.218 36	0.075 35	0.500 25	0.688 32	0.007 43	0.698 24	0.301 36	0.459 40	0.200 36
Tan: HCFS3D: Hierarchical Coupled Feature Selection Network for 3D Semantic and Instance Segmentation.
PanopticFusion-inst	0.478 29	0.667 29	0.712 28	0.595 23	0.259 34	0.550 35	0.000 37	0.613 21	0.175 32	0.250 36	0.434 23	0.437 16	0.411 33	0.857 22	0.485 21	0.591 34	0.267 40	0.944 28	0.359 27
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
UNet-backbone	0.319 36	0.667 29	0.715 27	0.233 35	0.189 36	0.479 39	0.008 33	0.218 36	0.067 38	0.201 37	0.173 37	0.107 34	0.123 40	0.438 36	0.150 35	0.615 32	0.355 33	0.916 30	0.093 42

Region	0.248 39	0.667 29	0.437 38	0.188 37	0.153 39	0.491 37	0.000 37	0.208 37	0.094 37	0.153 38	0.099 39	0.057 37	0.217 39	0.119 40	0.039 39	0.466 38	0.302 35	0.640 39	0.140 39

SemRegionNet	0.250 38	0.333 40	0.613 33	0.229 36	0.163 37	0.493 36	0.000 37	0.304 34	0.107 35	0.147 39	0.100 38	0.052 38	0.231 36	0.119 40	0.039 39	0.445 39	0.325 34	0.654 38	0.141 38

ASIS	0.199 41	0.333 40	0.253 42	0.167 40	0.140 40	0.438 40	0.000 37	0.177 39	0.008 41	0.121 40	0.069 40	0.004 43	0.231 37	0.429 37	0.036 41	0.445 40	0.273 38	0.333 42	0.119 41

3D-BEVIS	0.248 39	0.667 29	0.566 34	0.076 42	0.035 43	0.394 41	0.027 31	0.035 42	0.098 36	0.099 41	0.030 42	0.025 41	0.098 41	0.375 38	0.126 36	0.604 33	0.181 41	0.854 36	0.171 37
Cathrin Elich, Francis Engelmann, Jonas Schult, Theodora Kontogianni, Bastian Leibe: 3D-BEVIS: Birds-Eye-View Instance Segmentation.
Sgpn_scannet	0.143 42	0.208 43	0.390 41	0.169 39	0.065 41	0.275 42	0.029 30	0.069 40	0.000 42	0.087 42	0.043 41	0.014 42	0.027 43	0.000 42	0.112 38	0.351 42	0.168 42	0.438 41	0.138 40

MaskRCNN 2d->3d Proj	0.058 43	0.333 40	0.002 43	0.000 43	0.053 42	0.002 43	0.002 36	0.021 43	0.000 42	0.045 43	0.024 43	0.238 27	0.065 42	0.000 42	0.014 42	0.107 43	0.020 43	0.110 43	0.006 43

Method	avg iou	bathtub	bed	bookshelf	cabinet	chair	counter	curtain	desk	door	floor	otherfurniture	picture	refrigerator	shower curtain	sink	sofa	table	toilet	wall	window

Virtual MVFusion (R)	0.745 1	0.861 1	0.839 1	0.881 1	0.672 1	0.512 1	0.422 11	0.898 1	0.723 1	0.714 1	0.954 2	0.454 1	0.509 1	0.773 1	0.895 1	0.756 1	0.820 1	0.653 1	0.935 1	0.891 1	0.728 1
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru: Virtual Multi-view Fusion for 3D Semantic Segmentation. ECCV 2020
CU-Hybrid-2D Net	0.636 3	0.825 2	0.820 2	0.179 17	0.648 3	0.463 3	0.549 1	0.742 4	0.676 2	0.628 2	0.961 1	0.420 2	0.379 5	0.684 4	0.381 11	0.732 2	0.723 3	0.599 2	0.827 9	0.851 2	0.634 4

BPNet_2D	0.670 2	0.822 3	0.795 3	0.836 2	0.659 2	0.481 2	0.451 7	0.769 3	0.656 3	0.567 3	0.931 3	0.395 3	0.390 4	0.700 2	0.534 3	0.689 6	0.770 2	0.574 3	0.865 4	0.831 3	0.675 3
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia and Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
DMMF_3d	0.605 5	0.651 7	0.744 7	0.782 3	0.637 4	0.387 4	0.536 2	0.732 5	0.590 6	0.540 4	0.856 14	0.359 7	0.306 11	0.596 7	0.539 2	0.627 13	0.706 4	0.497 7	0.785 13	0.757 12	0.476 14

CMX	0.613 4	0.681 6	0.725 8	0.502 11	0.634 5	0.297 13	0.478 5	0.830 2	0.651 4	0.537 5	0.924 4	0.375 4	0.315 10	0.686 3	0.451 9	0.714 3	0.543 15	0.504 5	0.894 3	0.823 4	0.688 2

RFBNet	0.592 8	0.616 8	0.758 4	0.659 6	0.581 8	0.330 9	0.469 6	0.655 11	0.543 10	0.524 6	0.924 4	0.355 8	0.336 8	0.572 9	0.479 8	0.671 9	0.648 6	0.480 8	0.814 11	0.814 5	0.614 7

DCRedNet	0.583 9	0.682 5	0.723 9	0.542 10	0.510 12	0.310 11	0.451 7	0.668 9	0.549 9	0.520 7	0.920 6	0.375 4	0.446 2	0.528 12	0.417 10	0.670 10	0.577 13	0.478 9	0.862 5	0.806 6	0.628 6

SSMA	0.577 10	0.695 4	0.716 11	0.439 13	0.563 9	0.314 10	0.444 9	0.719 6	0.551 8	0.503 8	0.887 11	0.346 10	0.348 7	0.603 5	0.353 13	0.709 4	0.600 11	0.457 11	0.901 2	0.786 7	0.599 8
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
MCA-Net	0.595 7	0.533 13	0.756 5	0.746 5	0.590 6	0.334 8	0.506 3	0.670 8	0.587 7	0.500 9	0.905 9	0.366 6	0.352 6	0.601 6	0.506 6	0.669 11	0.648 6	0.501 6	0.839 8	0.769 10	0.516 13

FuseNet	0.535 12	0.570 11	0.681 13	0.182 16	0.512 11	0.290 14	0.431 10	0.659 10	0.504 13	0.495 10	0.903 10	0.308 11	0.428 3	0.523 13	0.365 12	0.676 7	0.621 10	0.470 10	0.762 14	0.779 8	0.541 10
Caner Hazirbas, Lingni Ma, Csaba Domokos, Daniel Cremers: FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture. ACCV 2016
DMMF	0.597 6	0.543 12	0.755 6	0.749 4	0.585 7	0.338 6	0.494 4	0.704 7	0.598 5	0.494 11	0.911 7	0.347 9	0.327 9	0.593 8	0.527 4	0.675 8	0.646 8	0.513 4	0.842 7	0.774 9	0.527 12

MSeg1080_RVC	0.485 15	0.505 14	0.709 12	0.092 18	0.427 15	0.241 15	0.411 12	0.654 12	0.385 18	0.457 12	0.861 13	0.053 18	0.279 12	0.503 14	0.481 7	0.645 12	0.626 9	0.365 16	0.748 16	0.725 14	0.529 11
John Lambert, Zhuang Liu, Ozan Sener, James Hays, Vladlen Koltun: MSeg: A Composite Dataset for Multi-domain Semantic Segmentation. CVPR 2020
SN_RN152pyrx8_RVC	0.546 11	0.572 10	0.663 14	0.638 8	0.518 10	0.298 12	0.366 16	0.633 13	0.510 12	0.446 13	0.864 12	0.296 12	0.267 13	0.542 11	0.346 14	0.704 5	0.575 14	0.431 13	0.853 6	0.766 11	0.630 5

ILC-PSPNet	0.475 16	0.490 15	0.581 16	0.289 15	0.507 13	0.067 18	0.379 14	0.610 15	0.417 16	0.435 14	0.822 17	0.278 13	0.267 13	0.503 14	0.228 15	0.616 15	0.533 16	0.375 15	0.820 10	0.729 13	0.560 9

3DMV (2d proj)	0.498 14	0.481 16	0.612 15	0.579 9	0.456 14	0.343 5	0.384 13	0.623 14	0.525 11	0.381 15	0.845 15	0.254 14	0.264 15	0.557 10	0.182 16	0.581 16	0.598 12	0.429 14	0.760 15	0.661 17	0.446 16
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
AdapNet++	0.503 13	0.613 9	0.722 10	0.418 14	0.358 18	0.337 7	0.370 15	0.479 16	0.443 14	0.368 16	0.907 8	0.207 15	0.213 17	0.464 16	0.525 5	0.618 14	0.657 5	0.450 12	0.788 12	0.721 15	0.408 17
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. International Journal of Computer Vision, 2019
Enet (reimpl)	0.376 17	0.264 18	0.452 18	0.452 12	0.365 16	0.181 16	0.143 18	0.456 17	0.409 17	0.346 17	0.769 18	0.164 16	0.218 16	0.359 17	0.123 18	0.403 18	0.381 18	0.313 18	0.571 17	0.685 16	0.472 15
Re-implementation of Adam Paszke, Abhishek Chaurasia, Sangpil Kim, Eugenio Culurciello: ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation.
ScanNet (2d proj)	0.330 18	0.293 17	0.521 17	0.657 7	0.361 17	0.161 17	0.250 17	0.004 18	0.440 15	0.183 18	0.836 16	0.125 17	0.060 18	0.319 18	0.132 17	0.417 17	0.412 17	0.344 17	0.541 18	0.427 18	0.109 18
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17

Method	avg ap	bathtub	bed	bookshelf	cabinet	chair	counter	curtain	desk	door	otherfurniture	picture	refrigerator	shower curtain	sink	sofa	table	toilet	window

UniDet_RVC	0.205 1	0.381 1	0.323 1	0.037 1	0.226 1	0.177 1	0.063 1	0.277 1	0.120 1	0.067 1	0.131 1	0.074 2	0.317 1	0.080 1	0.235 1	0.289 1	0.141 1	0.678 1	0.080 1

MaskRCNN_ScanNet	0.119 2	0.129 2	0.212 2	0.002 2	0.112 2	0.148 2	0.014 2	0.205 2	0.044 2	0.066 2	0.078 2	0.095 1	0.142 2	0.030 2	0.128 2	0.139 2	0.080 2	0.459 2	0.057 2
Re-implementation of Kaiming He, Georgia Gkioxari, Piotr Dollár, Ross Girshick: Mask R-CNN. ICCV'17

Method	avg recall	apartment	bathroom	bedroom / hotel	bookstore / library	conference room	copy/mail room	hallway	kitchen	laundry room	living room / lounge	misc	office	storage / basement / garage

3DASPP-SCE	0.691 2	0.500 1	0.938 2	0.824 3	1.000 1	1.000 1	0.500 2	1.000 1	0.857 2	0.500 2	0.556 3	0.000 2	0.812 2	0.500 1

multi-task	0.700 1	0.500 1	1.000 1	0.882 2	0.500 2	1.000 1	1.000 1	0.500 2	1.000 1	1.000 1	0.778 1	0.000 2	0.938 1	0.000 2
Shengyu Huang, Mikhail Usvyatsov, Konrad Schindler: Indoor Scene Recognition in 3D. IROS 2020
SE-ResNeXt-SSMA	0.498 3	0.000 4	0.812 3	0.941 1	0.500 2	0.500 3	0.500 2	0.500 2	0.429 4	0.500 2	0.667 2	0.500 1	0.625 3	0.000 2
Abhinav Valada, Rohit Mohan, Wolfram Burgard: Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. arXiv
resnet50_scannet	0.353 4	0.250 3	0.812 3	0.529 4	0.500 2	0.500 3	0.000 4	0.500 2	0.571 3	0.000 4	0.556 3	0.000 2	0.375 4	0.000 2

3D Semantic label benchmark

3D Semantic instance benchmark

2D Semantic label benchmark

2D Semantic instance benchmark

Scene type classification benchmark