mit-han-lab / flatformer
[CVPR'23] FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer
☆123Updated last year
Related projects ⓘ
Alternatives and complementary repositories for flatformer
- A fast and memory-efficient libarary for sparse transformer with varying token numbers (e.g., 3D point cloud).☆158Updated last year
- SCPNet: Semantic Scene Completion on Point Cloud (CVPR 2023, Highlight)☆105Updated last year
- GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds (CVPR 2023)☆116Updated last year
- [NIPS'24] Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection☆88Updated last month
- This is the official implementation of the paper - GeoMAE: Masked Geometric Target Prediction for Self-supervised Point Cloud Pre-Trainin…☆68Updated last year
- [CVPR 2024 Oral, Best Paper Award Candidate] Official repository of "PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness…☆167Updated last month
- ☆81Updated last year
- ☆154Updated last year
- Codes for ICLR 2024: "MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection"☆64Updated 4 months ago
- Code release for our NeurIPS 2023 paper "Uni3DETR: Unified 3D Detection Transformer", our ECCV 2024 paper "OV-Uni3DETR: Towards Unified O…☆81Updated 3 months ago
- Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds (CVPR 2022)☆193Updated last year
- Code for the paper "Masked Autoencoders for Self-Supervised Learning on Automotive Point Clouds"☆74Updated last year
- [IJCV 2024] P3Former: Position-Guided Point Cloud Panoptic Segmentation Transformer☆77Updated 7 months ago
- [NeurIPS 2024] Official code of ”LION: Linear Group RNN for 3D Object Detection in Point Clouds“☆124Updated last month
- Official implementation of our TIV'23 paper: Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occu…☆251Updated 10 months ago
- ScatterFormer: Efficient Voxel Transformer with Scattered Linear Attention (ECCV 2024)☆74Updated 3 months ago
- UniPAD: A Universal Pre-training Paradigm for Autonomous Driving (CVPR 2024)☆173Updated 4 months ago
- [CVPR 2023] LinK: Linear Kernel for LiDAR-based 3D Perception☆86Updated 3 months ago
- (ICCV2023) MonoNeRD: NeRF-like Representations for Monocular 3D Object Detection☆79Updated 10 months ago
- [AAAI 2024] BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios☆44Updated 3 months ago
- Efficient Point-based 3D Semantic Occupancy Prediction☆134Updated 3 months ago
- [CVPR 2024] PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation☆151Updated 2 months ago
- Open Source 3D Occupancy Prediction Library.☆136Updated last year
- ALSO: Automotive Lidar Self-supervision by Occupancy estimation☆168Updated last year
- Voxel Field Fusion for 3D Object Detection (CVPR2022)☆97Updated 2 years ago
- [CVPR 2023] FrustumFormer: Adaptive Instance-aware Resampling for Multi-view 3D Detection☆29Updated 3 months ago
- HEDNet (NeurIPS 2023) & SAFDNet (CVPR 2024 Oral)☆121Updated last month
- Sparse2Dense: Learning to Densify 3D Features for 3D Object Detection (NeurIPS 2022)☆69Updated last year
- [NeurIPS2022] This is the official code of "CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds".☆92Updated last year
- MSF: Motion-guided Sequential Fusion for Efficient 3D Object Detection from Point Cloud Sequences (CVPR 2023)☆57Updated last year