Semantic Segmentation On Scannet

Metrics

test mIoU

val mIoU

Results

Performance results of various models on this benchmark

			Paper Title
PTv3 ARKit LabelMaker	79.8	79.1	ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding
DITR	79.7	80.5	DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation
PTv3 + PPT	79.4	78.6	Point Transformer V3: Simpler, Faster, Stronger
PonderV2 + SparseUNet	78.5	77.0	PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm
Mix3D	78.1	73.6	Mix3D: Out-of-Context Data Augmentation for 3D Scenes
Swin3D-L	77.9	77.5	Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding
OctFormer	76.6	75.7	OctFormer: Octree-based Transformers for 3D Point Clouds
PPT + SparseUNet	76.6	76.4	Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training
PointHR	76.6	75.4	PointHR: Exploring High-Resolution Architectures for 3D Point Cloud Segmentation
O-CNN	76.2	74.0	O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis
OA-CNNs	75.6	76.1	OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation
LSK3DNet	75.5	75.7	LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels
PTv2	75.2	75.4	Point Transformer V2: Grouped Vector Attention and Partition-based Pooling
BPNet	74.9	73.9	Bidirectional Projection Network for Cross Dimension Scene Understanding
VMVF	74.6	-	Virtual Multi-view Fusion for 3D Semantic Segmentation
ODIN	74.4	77.8	ODIN: A Single Model for 2D and 3D Segmentation
EQ-Net	74.3	75.3	A Unified Query-based Paradigm for Point Cloud Understanding
StratifiedFormer	73.7	74.3	Stratified Transformer for 3D Point Cloud Segmentation
MinkowskiNet	73.4	72.2	4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks
SparseConvNet	72.5	69.3	3D Semantic Segmentation with Submanifold Sparse Convolutional Networks

0 of 45 row(s) selected.

Command Palette

Semantic Segmentation On Scannet

Metrics

Results