OpenCodePapers

semantic-segmentation-on-scannetv2

Semantic Segmentation
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeMean IoUPixel AccuracyMean IoU (test)Mean IoU (val)ModelNameReleaseDate
Efficient Prediction of Dense Visual Embeddings via Distillation and RGB-D Transformers✓ Link62.6%DVEFormer2026-01-01
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers✓ Link61.3%CMX2022-03-09
PanopticNDT: Efficient and Robust Panoptic Mapping✓ Link60.0%60.0%70.99%EMSANet (2x ResNet-34 NBt1D, PanopticNDT version)2023-09-24
RFBNet: Deep Multimodal Networks with Residual Fusion Blocks for RGB-D Semantic Segmentation59.2%RFBNet2019-06-29
Self-Supervised Model Adaptation for Multimodal Semantic Segmentation✓ Link57.7SSMA2018-08-11
Efficient Multi-Task Scene Analysis with RGB-D Transformers✓ Link56.4%EMSAFormer2023-06-08
Self-Supervised Model Adaptation for Multimodal Semantic Segmentation✓ Link50.3AdapNet++2018-08-11
3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation✓ Link49.8%3DMV (2d proj)2018-03-28
MSeg: A Composite Dataset for Multi-domain Semantic Segmentation✓ Link48.5%MSeg1080_RVC2021-12-27
Pyramid Scene Parsing Network✓ Link47.5%PSPNet2016-12-04
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation✓ Link37.6%ENet2016-06-07
ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes✓ Link33.0%ScanNet (2d proj)2017-02-14
Floors are Flat: Leveraging Semantics for Real-Time Surface Normal Prediction✓ Link65.6Floors are Flat2019-06-16
Check out how to contribute new results. Then edit this file on GitLab or GitHub.