dvlab-research / SparseTransformer
A fast and memory-efficient libarary for sparse transformer with varying token numbers (e.g., 3D point cloud).
☆160Updated last year
Alternatives and similar repositories for SparseTransformer:
Users that are interested in SparseTransformer are comparing it to the libraries listed below
- [CVPR'23] FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer☆125Updated last year
- This is the official implementation of the paper - GeoMAE: Masked Geometric Target Prediction for Self-supervised Point Cloud Pre-Trainin…☆68Updated last year
- GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds (CVPR 2023)☆122Updated last year
- Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds (CVPR 2022)☆195Updated last year
- Official implementation of our TIV'23 paper: Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occu…☆262Updated last year
- ☆156Updated 2 years ago
- Code for the paper "Masked Autoencoders for Self-Supervised Learning on Automotive Point Clouds"☆77Updated last year
- Voxel Transformer for 3D object detection☆249Updated 2 years ago
- SCPNet: Semantic Scene Completion on Point Cloud (CVPR 2023, Highlight)☆116Updated last year
- Sparse2Dense: Learning to Densify 3D Features for 3D Object Detection (NeurIPS 2022)☆72Updated last year
- LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs (CVPR 2023)☆199Updated last year
- [NIPS'24] Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection☆107Updated 4 months ago
- The official implementation for "Spherical Transformer for LiDAR-based 3D Recognition" (CVPR 2023).☆323Updated last year
- [NeurIPS2022] This is the official code of "CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds".☆94Updated last year
- DeepVision3D is an open source toolbox for point-cloud understanding.☆120Updated 2 years ago
- (NeurlPS 2022) Towards Efficient 3D Object Detection with Knowledge Distillation☆118Updated last year
- [IJCV 2024] P3Former: Position-Guided Point Cloud Panoptic Segmentation Transformer☆78Updated 10 months ago
- [ECCV 2022] LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection☆107Updated last year
- Code release for our NeurIPS 2023 paper "Uni3DETR: Unified 3D Detection Transformer", our ECCV 2024 paper "OV-Uni3DETR: Towards Unified O…☆94Updated 6 months ago
- Voxel Field Fusion for 3D Object Detection (CVPR2022)☆99Updated 2 years ago
- [NeurIPS 2024] Official code of ”LION: Linear Group RNN for 3D Object Detection in Point Clouds“☆156Updated 4 months ago
- Efficient Point-based 3D Semantic Occupancy Prediction☆138Updated 7 months ago
- Repo of "MsSVT: Mixed-scale Sparse Voxel Transformer for 3D Object Detection on Point Clouds".☆39Updated last year
- Official repository for TPAMI2024 "A Survey of Label-Efficient Deep Learning for 3D Point Clouds"☆55Updated last year
- Fully Sparse Fusion for 3D Object Detection☆90Updated 7 months ago
- CVPR 2023: Official code for `Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting'☆220Updated 10 months ago
- ☆87Updated last year
- (NeurlPS 2022) Spatial Pruned Sparse Convolution for Efficient 3D Object Detection☆63Updated 2 years ago
- HEDNet (NeurIPS 2023) & SAFDNet (CVPR 2024 Oral)☆137Updated 4 months ago
- An Efficient, Flexible, and General deep learning framework that retains minimal.☆111Updated last year