A fast and memory-efficient libarary for sparse transformer with varying token numbers (e.g., 3D point cloud).
☆170Sep 6, 2023Updated 2 years ago
Alternatives and similar repositories for SparseTransformer
Users that are interested in SparseTransformer are comparing it to the libraries listed below
Sorting:
- The official implementation for "Spherical Transformer for LiDAR-based 3D Recognition" (CVPR 2023).☆364Jun 8, 2023Updated 2 years ago
- ☆163Jan 6, 2023Updated 3 years ago
- Long Range 3D Perception - VoxelNeXt (CVPR 2023)☆856Jun 3, 2023Updated 2 years ago
- Voxel Transformer for 3D object detection☆257Jul 8, 2022Updated 3 years ago
- Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds (CVPR 2022)☆202Mar 22, 2023Updated 2 years ago
- Focal Sparse Convolutional Networks for 3D Object Detection (CVPR 2022, Oral)☆389Jun 1, 2023Updated 2 years ago
- We extend Segment Anything to 3D perception by combining it with VoxelNeXt.☆563Apr 18, 2023Updated 2 years ago
- [IJCV 2024] P3Former: Position-Guided Point Cloud Panoptic Segmentation Transformer☆91Apr 2, 2024Updated last year
- [CVPR 2023 Highlight] LaserMix for Semi-Supervised LiDAR Semantic Segmentation☆319Dec 6, 2025Updated 3 months ago
- (NeurlPS 2022) Spatial Pruned Sparse Convolution for Efficient 3D Object Detection☆65Jan 6, 2023Updated 3 years ago
- Repo of "MsSVT: Mixed-scale Sparse Voxel Transformer for 3D Object Detection on Point Clouds".☆38Sep 20, 2023Updated 2 years ago
- [CVPR 2023] PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection☆78May 23, 2023Updated 2 years ago
- An Efficient, Flexible, and General deep learning framework that retains minimal.☆130Dec 25, 2023Updated 2 years ago
- 🔥(CVPR 2023) Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation☆98Aug 11, 2024Updated last year
- LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs (CVPR 2023)☆214Jun 16, 2023Updated 2 years ago
- Official PyTorch implementation of the NeurIPS2022 paper "PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds"☆74May 19, 2023Updated 2 years ago
- [MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.☆1,447Feb 24, 2025Updated last year
- [CVPR2023] Official Implementation of "DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets"☆451Sep 4, 2024Updated last year
- [ICLR 2024] MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection☆75Jul 10, 2024Updated last year
- OpenPCSeg: Open Source Point Cloud Segmentation Toolbox and Benchmark☆482Apr 27, 2025Updated 10 months ago
- [NeurIPS'22] An official PyTorch implementation of PTv2.☆431Jun 4, 2023Updated 2 years ago
- [CVPR'23] FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer☆141Oct 27, 2023Updated 2 years ago
- ☆31Mar 24, 2023Updated 2 years ago
- 🔥(ECCV 2024 Oral) RAPiD-Seg: Range-Aware Pointwise Distance Distribution Networks for 3D LiDAR Segmentation☆49Sep 2, 2025Updated 6 months ago
- Implementation of ECCV2022 paper - LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation☆34Nov 22, 2022Updated 3 years ago
- [ECCV 2020] Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution☆619Jul 11, 2024Updated last year
- AziNorm: Exploiting the Radial Symmetry of Point Cloud for Azimuth-Normalized 3D Perception, CVPR 2022.☆54Sep 15, 2022Updated 3 years ago
- Official implementation of our TIV'23 paper: Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occu…☆280Dec 19, 2023Updated 2 years ago
- Unifying Voxel-based Representation with Transformer for 3D Object Detection (NeurIPS 2022)☆249Oct 19, 2022Updated 3 years ago
- DeepVision3D is an open source toolbox for point-cloud understanding.☆122May 16, 2022Updated 3 years ago
- [ICCV 2023] Cross Modal Transformer: Towards Fast and Robust 3D Object Detection☆410Oct 7, 2023Updated 2 years ago
- Pointcept: Perceive the world with sparse points, a codebase for point cloud perception research. Latest works: Utonia, Concerto (NeurIPS…☆2,893Mar 4, 2026Updated 2 weeks ago
- [ICCV 2023] Official PyTorch implementation of FocalFormer3D☆206Jan 2, 2025Updated last year
- OctFormer: Octree-based Transformers for 3D Point Clouds [SIGGRAPH 2023]☆350Nov 15, 2025Updated 4 months ago
- Benchmarking various sparse convolution libraries: MinkowskiEngine, SpConv, TorchSparse, and Open3D.☆13Apr 10, 2023Updated 2 years ago
- Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation (CVPR 2022)☆499May 31, 2024Updated last year
- Implementation for CenterFormer: Center-based Transformer for 3D Object Detection (ECCV 2022)☆304Dec 9, 2022Updated 3 years ago
- [AAAI 2023] PolarFormer: Multi-camera 3D Object Detection with Polar Transformers☆176Feb 6, 2023Updated 3 years ago
- Point Density-Aware Voxels for LiDAR 3D Object Detection (CVPR 2022)☆164Oct 2, 2022Updated 3 years ago