|
PTv3 ARKit LabelMaker
|
ARKit LabelMaker: A New Scale for Indoor 3D Scene…
|
79.80
|
2024-10-17
|
|
|
DITR
|
DINO in the Room: Leveraging 2D Foundation Models…
|
79.70
|
2025-03-24
|
|
|
Sonata + PTv3
|
Sonata: Self-Supervised Learning of Reliable Poin…
|
79.40
|
2025-03-20
|
|
|
PTv3 + PPT
|
Point Transformer V3: Simpler, Faster, Stronger
|
79.40
|
2023-12-15
|
|
|
PonderV2 + SparseUNet
|
PonderV2: Pave the Way for 3D Foundation Model wi…
|
78.50
|
2023-10-12
|
|
|
Mix3D
|
Mix3D: Out-of-Context Data Augmentation for 3D Sc…
|
78.10
|
2021-10-05
|
|
|
BFANet
|
BFANet: Revisiting 3D Semantic Segmentation with …
|
78.00
|
2025-03-16
|
|
|
Swin3D-L
|
Swin3D: A Pretrained Transformer Backbone for 3D …
|
77.90
|
2023-04-14
|
|
|
Pamba
|
Pamba: Enhancing Global Interaction in Point Clou…
|
77.60
|
2024-06-25
|
|
|
Serialized Piont Mamba
|
Serialized Point Mamba: A Serialized Point Cloud …
|
76.80
|
2024-07-17
|
|
|
OneFormer3D
|
OneFormer3D: One Transformer for Unified Point Cl…
|
76.60
|
2023-11-24
|
|
|
PPT + SparseUNet
|
Towards Large-scale 3D Representation Learning wi…
|
76.60
|
2023-08-18
|
|
|
OctFormer
|
OctFormer: Octree-based Transformers for 3D Point…
|
76.60
|
2023-05-04
|
|
|
PointHR
|
PointHR: Exploring High-Resolution Architectures …
|
76.60
|
2023-10-11
|
|
|
KPConvX-L
|
KPConvX: Modernizing Kernel Point Convolution wit…
|
76.30
|
2024-05-21
|
|
|
O-CNN
|
O-CNN: Octree-based Convolutional Neural Networks…
|
76.20
|
2017-12-05
|
|
|
AVS-Net
|
AVS-Net: Point Sampling with Adaptive Voxel Size …
|
76.10
|
2024-02-27
|
|
|
DeLA
|
Decoupled Local Aggregation for Point Cloud Learn…
|
75.90
|
2023-08-31
|
|
|
OA-CNNs
|
OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semanti…
|
75.60
|
2024-03-21
|
|
|
LSK3DNet
|
LSK3DNet: Towards Effective and Efficient 3D Perc…
|
75.50
|
2024-03-22
|
|
|
MSC + SparseUNet
|
Masked Scene Contrast: A Scalable Framework for U…
|
75.50
|
2023-03-24
|
|
|
PTv2
|
Point Transformer V2: Grouped Vector Attention an…
|
75.20
|
2022-10-11
|
|
|
BPNet
|
Bidirectional Projection Network for Cross Dimens…
|
74.90
|
2021-03-26
|
|
|
VMVF
|
Virtual Multi-view Fusion for 3D Semantic Segment…
|
74.60
|
2020-07-26
|
|
|
ODIN
|
ODIN: A Single Model for 2D and 3D Segmentation
|
74.40
|
2024-01-04
|
|
|
EQ-Net
|
A Unified Query-based Paradigm for Point Cloud Un…
|
74.30
|
2022-03-02
|
|
|
StratifiedFormer
|
Stratified Transformer for 3D Point Cloud Segment…
|
73.70
|
2022-03-28
|
|
|
MinkowskiNet
|
4D Spatio-Temporal ConvNets: Minkowski Convolutio…
|
73.40
|
2019-04-18
|
|
|
SparseConvNet
|
3D Semantic Segmentation with Submanifold Sparse …
|
72.50
|
2017-11-28
|
|
|
FG-Net
|
FG-Net: Fast Large-Scale LiDAR Point Clouds Under…
|
69.00
|
2020-12-17
|
|
|
RPNet
|
Learning Inner-Group Relations on Point Clouds
|
68.20
|
2021-08-27
|
|
|
PanopticNDT (10cm)
|
PanopticNDT: Efficient and Robust Panoptic Mapping
|
68.10
|
2023-09-24
|
|
|
KpConv
|
KPConv: Flexible and Deformable Convolution for P…
|
68.00
|
2019-04-18
|
|
|
SAFNet
|
Similarity-Aware Fusion Network for 3D Semantic S…
|
65.40
|
2021-07-04
|
|
|
TextureNet
|
TextureNet: Consistent Local Parametrizations for…
|
56.60
|
2018-11-30
|
|
|
PointConv
|
PointConv: Deep Convolutional Networks on 3D Poin…
|
55.60
|
2018-11-17
|
|
|
PanopticFusion
|
PanopticFusion: Online Volumetric Semantic Mappin…
|
52.90
|
2019-03-04
|
|
|
3DMV
|
3DMV: Joint 3D-Multi-View Prediction for 3D Seman…
|
48.40
|
2018-03-28
|
|
|
FCPN
|
Fully-Convolutional Point Networks for Large-Scal…
|
44.70
|
2018-08-21
|
|
|
SurfaceConvPF
|
PFCNN: Convolutional Neural Networks on 3D Surfac…
|
44.20
|
2018-08-15
|
|
|
Tangent Convolutions
|
Tangent Convolutions for Dense Prediction in 3D
|
44.20
|
2018-07-06
|
|
|
SPLAT Net
|
SPLATNet: Sparse Lattice Networks for Point Cloud…
|
39.30
|
2018-02-22
|
|
|
PointNet++
|
PointNet++: Deep Hierarchical Feature Learning on…
|
33.90
|
2017-06-07
|
|
|
ScanNet
|
ScanNet: Richly-annotated 3D Reconstructions of I…
|
30.60
|
2017-02-14
|
|