Semantic Segmentation On S3Dis

Metrics

Mean IoU

Number of params

oAcc

Results

Performance results of various models on this benchmark

				Paper Title
Sonata + PTv3	82.3	128M	93.3	Sonata: Self-Supervised Learning of Reliable Point Representations
PTv3 + PPT	80.8	24.1M	92.6	Point Transformer V3: Simpler, Faster, Stronger
PonderV2 + SparseUNet	79.9	-	92.5	PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm
Swin3D-L	79.8	N/A	92.4	Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding
PointVector-XL	78.4	-	91.9	PointVector: A Vector Representation In Point Cloud Analysis
PPT + SparseUNet	78.1	N/A	92.2	Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training
WindowNorm+StratifiedTransformer	77.6	8.2M	91.7	Window Normalization: Enhancing Point Cloud Understanding by Unifying Inconsistent Point Densities
EQ-Net	77.5	N/A	-	A Unified Query-based Paradigm for Point Cloud Understanding
PointMetaBase-XXL	77.0	19.7M	91.3	Meta Architecture for Point Cloud Analysis
Superpoint Transformer	76.0	0.212M	90.4	Efficient 3D Semantic Segmentation with Superpoint Transformer
SuperCluster	75.3	0.21M	-	Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering
PointNeXt-XL	74.9	41.6M	90.3	PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies
DeepViewAgg	74.7	41.2M	90.1	Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation
RepSurf-U	74.3	0.97M	90.8	Surface Representation for Point Clouds
WindowNorm+PointTransformer	74.1	8.0M	90.2	Window Normalization: Enhancing Point Cloud Understanding by Unifying Inconsistent Point Densities
PointNeXt-L	73.9	7.1M	89.9	PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies
PointTransformer	73.5	7.8M	90.2	Point Transformer
CBL	73.1	N/A	89.6	Contrastive Boundary Learning for Point Cloud Segmentation
BAAF-Net	72.2	N/A	88.9	Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion
SCF-Net	71.6	N/A	88.4	SCF-Net: Learning Spatial Contextual Features for Large-Scale Point Cloud Segmentation

0 of 54 row(s) selected.

Command Palette

Semantic Segmentation On S3Dis

Metrics

Results