HyperAIHyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Semantic Segmentation On Scannetv2

Metrics

Mean IoU

Results

Performance results of various models on this benchmark

Model Name
Mean IoU
Paper TitleRepository
PSPNet47.5%Pyramid Scene Parsing Network-
CMX61.3%CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers-
AdapNet++50.3Self-Supervised Model Adaptation for Multimodal Semantic Segmentation-
ENet37.6%ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation-
ScanNet (2d proj)33.0%ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes-
SSMA57.7Self-Supervised Model Adaptation for Multimodal Semantic Segmentation-
Floors are Flat-Floors are Flat: Leveraging Semantics for Real-Time Surface Normal Prediction-
RFBNet59.2%RFBNet: Deep Multimodal Networks with Residual Fusion Blocks for RGB-D Semantic Segmentation-
EMSAFormer56.4%Efficient Multi-Task Scene Analysis with RGB-D Transformers-
EMSANet (2x ResNet-34 NBt1D, PanopticNDT version)60.0%PanopticNDT: Efficient and Robust Panoptic Mapping-
3DMV (2d proj)49.8%3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation-
MSeg1080_RVC48.5%MSeg: A Composite Dataset for Multi-domain Semantic Segmentation-
0 of 12 row(s) selected.
Semantic Segmentation On Scannetv2 | SOTA | HyperAI