HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Semantic Segmentation On Scannet

Metrics

test mIoU
val mIoU

Results

Performance results of various models on this benchmark

Paper Title
PTv3 ARKit LabelMaker79.879.1ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding
DITR79.780.5DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation
PTv3 + PPT79.478.6Point Transformer V3: Simpler, Faster, Stronger
PonderV2 + SparseUNet78.577.0PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm
Mix3D78.173.6Mix3D: Out-of-Context Data Augmentation for 3D Scenes
Swin3D-L77.977.5Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding
OctFormer76.675.7OctFormer: Octree-based Transformers for 3D Point Clouds
PPT + SparseUNet76.676.4Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training
PointHR76.675.4PointHR: Exploring High-Resolution Architectures for 3D Point Cloud Segmentation
O-CNN76.274.0O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis
OA-CNNs75.676.1OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation
LSK3DNet75.575.7LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels
PTv275.275.4Point Transformer V2: Grouped Vector Attention and Partition-based Pooling
BPNet74.973.9Bidirectional Projection Network for Cross Dimension Scene Understanding
VMVF74.6-Virtual Multi-view Fusion for 3D Semantic Segmentation
ODIN74.477.8ODIN: A Single Model for 2D and 3D Segmentation
EQ-Net74.375.3A Unified Query-based Paradigm for Point Cloud Understanding
StratifiedFormer73.774.3Stratified Transformer for 3D Point Cloud Segmentation
MinkowskiNet73.472.24D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks
SparseConvNet72.569.33D Semantic Segmentation with Submanifold Sparse Convolutional Networks
0 of 45 row(s) selected.
Semantic Segmentation On Scannet | SOTA | HyperAI