ScanNet200

Overview edit

Variants: ScanNet200

Associated Benchmarks

This dataset is used in 3 benchmarks:

• 3D Semantic Segmentation - Metrics: val mIoU, test mIoU
• 3D Open-Vocabulary Instance Segmentation - Metrics: mAP, AP50, AP25, AP Head, AP Common, AP Tail
• 3D Instance Segmentation - Metrics: mAP, mAP@25, mAP@50

Recent Benchmark Submissions

Research Papers

Recent papers with results on this dataset:

• DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation (2025) -
• Sonata: Self-Supervised Learning of Reliable Point Representations (2025) -
• BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis (2025) -
• Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking (2024) -
• MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation (2024) -
• ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding (2024) -
• Pamba: Enhancing Global Interaction in Point Clouds via State Space Model (2024) -
• Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance Segmentation (2024) -
• LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels (2024) -
• OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation (2024) -
• ODIN: A Single Model for 2D and 3D Segmentation (2024) -
• Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance (2023) -
• Point Transformer V3: Simpler, Faster, Stronger (2023) -
• OneFormer3D: One Transformer for Unified Point Cloud Segmentation (2023) -
• PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm (2023) -
• OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation (2023) -
• Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training (2023) -
• OpenMask3D: Open-Vocabulary 3D Instance Segmentation (2023) -
• OctFormer: Octree-based Transformers for 3D Point Clouds (2023) -
• ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution (2023) -