Papers with Code · CC BY-SA 4.0

S3DIS

아카이브 평가 54건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
Sonata + PTv3	Mean IoU 82.3 mAcc 89.9 oAcc 93.3 Number of params 128M	Sonata: Self-Supervised Learning of Reliable Point Representations 2025-03-20	코드 1 · 코드 2
PTv3 + PPT	Mean IoU 80.8 mAcc 87.7 oAcc 92.6 Number of params 24.1M	Point Transformer V3: Simpler, Faster, Stronger 2023-12-15	코드 1 · 코드 2 · 코드 3
PonderV2 + SparseUNet	Mean IoU 79.9 mAcc 86.5 oAcc 92.5	PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm 2023-10-12	코드 1
Swin3D-L	Mean IoU 79.8 mAcc 88.0 oAcc 92.4 Number of params N/A	Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding 2023-04-14	코드 1 · 코드 2
PointVector-XL	Mean IoU 78.4 mAcc 86.1 oAcc 91.9 Params (M) 24.1	PointVector: A Vector Representation In Point Cloud Analysis 2022-05-21	코드 1
PPT + SparseUNet	Mean IoU 78.1 mAcc 85.4 oAcc 92.2 Number of params N/A	Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training 2023-08-18	코드 1
WindowNorm+StratifiedTransformer	Mean IoU 77.6 mAcc 85.8 oAcc 91.7 Number of params 8.2M Params (M) 8.2	Window Normalization: Enhancing Point Cloud Understanding by Unifying Inconsistent Point Densities 2022-12-05	코드 1
EQ-Net	Mean IoU 77.5 Number of params N/A	A Unified Query-based Paradigm for Point Cloud Understanding 2022-03-02	코드 1
PointMetaBase-XXL	Mean IoU 77.0 oAcc 91.3 FLOPs 11.0G Number of params 19.7M Params (M) 19.7	Meta Architecture for Point Cloud Analysis 2022-11-26	코드 1
Superpoint Transformer	mIoU 76.0 Mean IoU 76.0 mAcc 85.8 oAcc 90.4 Number of params 0.212M Params (M) 0.212	Efficient 3D Semantic Segmentation with Superpoint Transformer 2023-06-13	코드 1
SuperCluster	Mean IoU 75.3 Number of params 0.21M Params (M) 0.21	Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering 2024-01-12	코드 1
PointNeXt-XL	Mean IoU 74.9 mAcc 83.0 oAcc 90.3 FLOPs 84.8G Number of params 41.6M Params (M) 41.6	PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies 2022-06-09	코드 1 · 코드 2 · 코드 3
DeepViewAgg	Mean IoU 74.7 mAcc 83.8 oAcc 90.1 Number of params 41.2M Params (M) 41.2	Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation 2022-04-15	코드 1
RepSurf-U	Mean IoU 74.3 mAcc 82.6 oAcc 90.8 FLOPs 1.04G Number of params 0.97M Params (M) 0.97	Surface Representation for Point Clouds 2022-05-11	코드 1
WindowNorm+PointTransformer	Mean IoU 74.1 mAcc 82.5 oAcc 90.2 Number of params 8.0M Params (M) 8	Window Normalization: Enhancing Point Cloud Understanding by Unifying Inconsistent Point Densities 2022-12-05	코드 1
PointNeXt-L	Mean IoU 73.9 mAcc 82.2 oAcc 89.9 FLOPs 15.2G Number of params 7.1M Params (M) 7.1	PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies 2022-06-09	코드 1 · 코드 2 · 코드 3
PointTransformer	Mean IoU 73.5 mAcc 81.9 oAcc 90.2 Number of params 7.8M Params (M) 7.8	Point Transformer 2020-12-16	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11 · 코드 12 · 코드 13 · 코드 14 · 코드 15 · 코드 16 · 코드 17 · 코드 18 · 코드 19 · 코드 20 · 코드 21 · 코드 22 · 코드 23 · 코드 24
CBL	Mean IoU 73.1 mAcc 79.4 oAcc 89.6 Number of params N/A	Contrastive Boundary Learning for Point Cloud Segmentation 2022-03-10	코드 1
BAAF-Net	Mean IoU 72.2 mAcc 83.1 oAcc 88.9 Number of params N/A	Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion 2021-03-12	코드 1 · 코드 2
SCF-Net	Mean IoU 71.6 mAcc 82.7 oAcc 88.4 Number of params N/A	SCF-Net: Learning Spatial Contextual Features for Large-Scale Point Cloud Segmentation 2021-06-19	코드 1
Feature Geometric Net (FG-Net)	Mean IoU 70.8 mAcc 82.9 oAcc 88.2 Number of params N/A	FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling 2020-12-17	코드 1
RPNet	Mean IoU 70.8 Number of params N/A	Learning Inner-Group Relations on Point Clouds 2021-08-27	코드 1
KPConv	Mean IoU 70.6 mAcc 79.1 Number of params 14.1M Params (M) 14.1	KPConv: Flexible and Deformable Convolution for Point Clouds 2019-04-18	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10
KPConv	Mean IoU 70.6 Number of params 14.1M Params (M) 14.1	Point Transformer 2020-12-16	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11 · 코드 12 · 코드 13 · 코드 14 · 코드 15 · 코드 16 · 코드 17 · 코드 18 · 코드 19 · 코드 20 · 코드 21 · 코드 22 · 코드 23 · 코드 24
FastPointTrans. (small)	Mean IoU 70.3 Number of params N/A	Fast Point Transformer 2021-12-09	코드 1
MuGNet	Mean IoU 69.8 oAcc 88.5 Number of params N/A	MuGNet: Multi-Resolution Graph Neural Network for Large-Scale Pointcloud Segmentation 2020-11-16	코드 1
PointASNL	Mean IoU 68.7 mAcc 79.0 oAcc 88.8 Number of params N/A	PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling 2020-03-01	코드 1
SSP+SPG	Mean IoU 68.4 mAcc 78.3 oAcc 87.9 Number of params 0.290M Params (M) 0.29	Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning 2019-04-03	코드 1 · 코드 2
FKAConv	Mean IoU 68.4 Number of params N/A	FKAConv: Feature-Kernel Alignment for Point Cloud Convolution 2020-04-09	코드 1
ConvPoint	Mean IoU 68.2 oAcc 88.8 Number of params 4.7M Params (M) 4.1	ConvPoint: Continuous Convolutions for Point Cloud Processing 2019-04-04	코드 1