AI Paper Atlas

Research map / Benchmarks / S3DIS

S3DIS leaderboard

30 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on S3DIS. Best mIoU: 80.1 (Wreath Product Net. + Attn, NeurIPS 2020).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

S3DIS · mIoU

30 papers, each with its best reported number for its own method; higher is better.

#mIoU ↑MethodPaperTopic
180.1Wreath Product Net. + AttnEquivariant Networks for Hierarchical Structures
NeurIPS 2020 · Table 1
Point cloud classification
279.6PCM-Tiny† with DeLA blocksPoint Cloud Mamba: Point Cloud Learning via State Space Model
AAAI 2025 · Table: 3D semantic segmentatio
Point cloud classification
377.1OursOmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning
CVPR 2024 · Table 6
Cross-modal learning
473.6CloudMambaCloudMamba: Grouped Selective State Spaces for Point Cloud Analysis
AAAI 2026 · Table 4
Point cloud classification
573.2PointClustering
SR-UNet
PointClustering: Unsupervised Point Cloud Pre-Training Using Transformation Invariance in Clustering
CVPR 2023 · Table 5
Point cloud classification
672.2Contrastive Scene Contexts
Sparse Res-UNet
Exploring Data-Efficient 3D Scene Understanding With Contrastive Scene Contexts
CVPR 2021 · Table: Downstream fine-tuning
Segmentation and detection
772GroupContrast
SparseUNet
GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding
CVPR 2024 · Table 2a
Segmentation and detection
872Exp. V
Stratified Transformer
Stratified Transformer for 3D Point Cloud Segmentation
CVPR 2022 · Table 4
Point cloud classification
971.8Ours
Plain Transformer
SAM-Guided Masked Token Prediction for 3D Scene Understanding
NeurIPS 2024 · Table 2
3D detection and driving
1071.6Point Transformer + X-3D
Point Transformer
X-3D: Explicit 3D Structure Modeling for Point Cloud Recognition
CVPR 2024 · Table 7
Point cloud classification
20 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.