Semantic Segmentation on ScanNet

Metric: test mIoU (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	test mIoU▼	Extra Data	Paper	Date↕	Code
1	PTv3 ARKit LabelMaker	79.8	Yes	ARKit LabelMaker: A New Scale for Indoor 3D Scen...	2024-10-17	Code
2	DITR	79.7	No	DINO in the Room: Leveraging 2D Foundation Model...	2025-03-24	Code
3	PTv3 + PPT	79.4	Yes	Point Transformer V3: Simpler, Faster, Stronger	2023-12-15	Code
4	PonderV2 + SparseUNet	78.5	Yes	PonderV2: Pave the Way for 3D Foundation Model w...	2023-10-12	Code
5	Mix3D	78.1	No	Mix3D: Out-of-Context Data Augmentation for 3D S...	2021-10-05	Code
6	Swin3D-L	77.9	Yes	Swin3D: A Pretrained Transformer Backbone for 3D...	2023-04-14	Code
7	PPT + SparseUNet	76.6	Yes	Towards Large-scale 3D Representation Learning w...	2023-08-18	Code
8	OctFormer	76.6	No	OctFormer: Octree-based Transformers for 3D Poin...	2023-05-04	Code
9	PointHR	76.6	No	PointHR: Exploring High-Resolution Architectures...	2023-10-11	Code
10	O-CNN	76.2	No	O-CNN: Octree-based Convolutional Neural Network...	2017-12-05	Code
11	OA-CNNs	75.6	No	OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semant...	2024-03-21	Code
12	LSK3DNet	75.5	No	LSK3DNet: Towards Effective and Efficient 3D Per...	2024-03-22	Code
13	PTv2	75.2	No	Point Transformer V2: Grouped Vector Attention a...	2022-10-11	Code
14	BPNet	74.9	No	Bidirectional Projection Network for Cross Dimen...	2021-03-26	Code
15	VMVF	74.6	No	Virtual Multi-view Fusion for 3D Semantic Segmen...	2020-07-26	Code
16	ODIN	74.4	No	ODIN: A Single Model for 2D and 3D Segmentation	2024-01-04	Code
17	EQ-Net	74.3	No	A Unified Query-based Paradigm for Point Cloud U...	2022-03-02	Code
18	StratifiedFormer	73.7	No	Stratified Transformer for 3D Point Cloud Segmen...	2022-03-28	Code
19	MinkowskiNet	73.4	No	4D Spatio-Temporal ConvNets: Minkowski Convoluti...	2019-04-18	Code
20	SparseConvNet	72.5	No	3D Semantic Segmentation with Submanifold Sparse...	2017-11-28	Code
21	FG-Net	69	No	FG-Net: Fast Large-Scale LiDAR Point Clouds Unde...	2020-12-17	Code
22	RPNet	68.2	No	Learning Inner-Group Relations on Point Clouds	2021-08-27	Code
23	PanopticNDT (10cm)	68.1	No	PanopticNDT: Efficient and Robust Panoptic Mapping	2023-09-24	Code
24	KpConv	68	No	KPConv: Flexible and Deformable Convolution for ...	2019-04-18	Code
25	SAFNet	65.4	No	Similarity-Aware Fusion Network for 3D Semantic ...	2021-07-04	Code
26	TextureNet	56.6	No	TextureNet: Consistent Local Parametrizations fo...	2018-11-30	Code
27	PointConv	55.6	No	PointConv: Deep Convolutional Networks on 3D Poi...	2018-11-17	Code
28	PanopticFusion	52.9	No	PanopticFusion: Online Volumetric Semantic Mappi...	2019-03-04	-
29	3DMV	48.4	No	3DMV: Joint 3D-Multi-View Prediction for 3D Sema...	2018-03-28	Code
30	PointCNN	45.8	No	-	-	Code
31	FCPN	44.7	No	Fully-Convolutional Point Networks for Large-Sca...	2018-08-21	Code
32	SurfaceConvPF	44.2	No	PFCNN: Convolutional Neural Networks on 3D Surfa...	2018-08-15	Code
33	Tangent Convolutions	44.2	No	Tangent Convolutions for Dense Prediction in 3D	2018-07-06	Code
34	SPLAT Net	39.3	No	SPLATNet: Sparse Lattice Networks for Point Clou...	2018-02-22	Code
35	PointNet++	33.9	No	PointNet++: Deep Hierarchical Feature Learning o...	2017-06-07	Code
36	ScanNet	30.6	No	ScanNet: Richly-annotated 3D Reconstructions of ...	2017-02-14	Code

#1PTv3 ARKit LabelMakerSOTA
79.8
test mIoU· Extra Data· 2024-10-17
ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding Code
#2DITR
79.7
test mIoU· 2025-03-24
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation Code
#3PTv3 + PPTSOTA
79.4
test mIoU· Extra Data· 2023-12-15
Point Transformer V3: Simpler, Faster, Stronger Code
#4PonderV2 + SparseUNetSOTA
78.5
test mIoU· Extra Data· 2023-10-12
PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm Code
#5Mix3DSOTA
78.1
test mIoU· 2021-10-05
Mix3D: Out-of-Context Data Augmentation for 3D Scenes Code
#6Swin3D-L
77.9
test mIoU· Extra Data· 2023-04-14
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding Code
#7PPT + SparseUNet
76.6
test mIoU· Extra Data· 2023-08-18
Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training Code
#8OctFormer
76.6
test mIoU· 2023-05-04
OctFormer: Octree-based Transformers for 3D Point Clouds Code
#9PointHR
76.6
test mIoU· 2023-10-11
PointHR: Exploring High-Resolution Architectures for 3D Point Cloud Segmentation Code
#10O-CNNSOTA
76.2
test mIoU· 2017-12-05
O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis Code
#11OA-CNNs
75.6
test mIoU· 2024-03-21
OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation Code
#12LSK3DNet
75.5
test mIoU· 2024-03-22
LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels Code
#13PTv2
75.2
test mIoU· 2022-10-11
Point Transformer V2: Grouped Vector Attention and Partition-based Pooling Code
#14BPNet
74.9
test mIoU· 2021-03-26
Bidirectional Projection Network for Cross Dimension Scene Understanding Code
#15VMVF
74.6
test mIoU· 2020-07-26
Virtual Multi-view Fusion for 3D Semantic Segmentation Code
#16ODIN
74.4
test mIoU· 2024-01-04
ODIN: A Single Model for 2D and 3D Segmentation Code
#17EQ-Net
74.3
test mIoU· 2022-03-02
A Unified Query-based Paradigm for Point Cloud Understanding Code
#18StratifiedFormer
73.7
test mIoU· 2022-03-28
Stratified Transformer for 3D Point Cloud Segmentation Code
#19MinkowskiNet
73.4
test mIoU· 2019-04-18
4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks Code
#20SparseConvNetSOTA
72.5
test mIoU· 2017-11-28
3D Semantic Segmentation with Submanifold Sparse Convolutional Networks Code
#21FG-Net
69
test mIoU· 2020-12-17
FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling Code
#22RPNet
68.2
test mIoU· 2021-08-27
Learning Inner-Group Relations on Point Clouds Code
#23PanopticNDT (10cm)
68.1
test mIoU· 2023-09-24
PanopticNDT: Efficient and Robust Panoptic Mapping Code
#24KpConv
68
test mIoU· 2019-04-18
KPConv: Flexible and Deformable Convolution for Point Clouds Code
#25SAFNet
65.4
test mIoU· 2021-07-04
Similarity-Aware Fusion Network for 3D Semantic Segmentation Code
#26TextureNet
56.6
test mIoU· 2018-11-30
TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes Code
#27PointConv
55.6
test mIoU· 2018-11-17
PointConv: Deep Convolutional Networks on 3D Point Clouds Code
#28PanopticFusion
52.9
test mIoU· 2019-03-04
PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things
#293DMV
48.4
test mIoU· 2018-03-28
3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation Code
#30PointCNN
45.8
test mIoU
No paperCode
#31FCPN
44.7
test mIoU· 2018-08-21
Fully-Convolutional Point Networks for Large-Scale Point Clouds Code
#32SurfaceConvPF
44.2
test mIoU· 2018-08-15
PFCNN: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames Code
#33Tangent Convolutions
44.2
test mIoU· 2018-07-06
Tangent Convolutions for Dense Prediction in 3D Code
#34SPLAT Net
39.3
test mIoU· 2018-02-22
SPLATNet: Sparse Lattice Networks for Point Cloud Processing Code
#35PointNet++SOTA
33.9
test mIoU· 2017-06-07
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space Code
#36ScanNetSOTA
30.6
test mIoU· 2017-02-14
ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes Code