3D Semantic Segmentation on ScanNet200

Metric: val mIoU (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	val mIoU▼	Extra Data	Paper	Date↕	Code
1	DITR	41.2	No	DINO in the Room: Leveraging 2D Foundation Model...	2025-03-24	Code
2	ODIN	40.5	No	ODIN: A Single Model for 2D and 3D Segmentation	2024-01-04	Code
3	PTv3 ArKitLabelmaker	40.3	Yes	ARKit LabelMaker: A New Scale for Indoor 3D Scen...	2024-10-17	Code
4	BFANet	37.3	No	BFANet: Revisiting 3D Semantic Segmentation with...	2025-03-16	Code
5	Sonata + PTv3	36.8	Yes	Sonata: Self-Supervised Learning of Reliable Poi...	2025-03-20	Code
6	Pamba	36.3	No	Pamba: Enhancing Global Interaction in Point Clo...	2024-06-25	-
7	PTv3 + PPT	36	Yes	Point Transformer V3: Simpler, Faster, Stronger	2023-12-15	Code
8	OA-CNNs	33.3	No	OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semant...	2024-03-21	Code
9	LSK3DNet	33.1	No	LSK3DNet: Towards Effective and Efficient 3D Per...	2024-03-22	Code
10	OctFormer	32.6	No	OctFormer: Octree-based Transformers for 3D Poin...	2023-05-04	Code
11	PonderV2 + SparseUNet	32.3	Yes	PonderV2: Pave the Way for 3D Foundation Model w...	2023-10-12	Code
12	PPT+SparseUNet	31.9	Yes	Towards Large-scale 3D Representation Learning w...	2023-08-18	Code
13	OneFormer3D	30.1	No	OneFormer3D: One Transformer for Unified Point C...	2023-11-24	Code
14	LGround	28.8	No	Language-Grounded Indoor 3D Semantic Segmentatio...	2022-04-16	Code
15	CSC	26.4	No	Exploring Data-Efficient 3D Scene Understanding ...	2020-12-16	Code
16	MinkUNet	25	No	4D Spatio-Temporal ConvNets: Minkowski Convoluti...	2019-04-18	Code

#1DITRSOTA
41.2
val mIoU· 2025-03-24
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation Code
#2ODINSOTA
40.5
val mIoU· 2024-01-04
ODIN: A Single Model for 2D and 3D Segmentation Code
#3PTv3 ArKitLabelmaker
40.3
val mIoU· Extra Data· 2024-10-17
ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding Code
#4BFANet
37.3
val mIoU· 2025-03-16
BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis Code
#5Sonata + PTv3
36.8
val mIoU· Extra Data· 2025-03-20
Sonata: Self-Supervised Learning of Reliable Point Representations Code
#6Pamba
36.3
val mIoU· 2024-06-25
Pamba: Enhancing Global Interaction in Point Clouds via State Space Model
#7PTv3 + PPTSOTA
36
val mIoU· Extra Data· 2023-12-15
Point Transformer V3: Simpler, Faster, Stronger Code
#8OA-CNNs
33.3
val mIoU· 2024-03-21
OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation Code
#9LSK3DNet
33.1
val mIoU· 2024-03-22
LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels Code
#10OctFormerSOTA
32.6
val mIoU· 2023-05-04
OctFormer: Octree-based Transformers for 3D Point Clouds Code
#11PonderV2 + SparseUNet
32.3
val mIoU· Extra Data· 2023-10-12
PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm Code
#12PPT+SparseUNet
31.9
val mIoU· Extra Data· 2023-08-18
Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training Code
#13OneFormer3D
30.1
val mIoU· 2023-11-24
OneFormer3D: One Transformer for Unified Point Cloud Segmentation Code
#14LGroundSOTA
28.8
val mIoU· 2022-04-16
Language-Grounded Indoor 3D Semantic Segmentation in the Wild Code
#15CSCSOTA
26.4
val mIoU· 2020-12-16
Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts Code
#16MinkUNetSOTA
25
val mIoU· 2019-04-18
4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks Code