NVlabs / DQTrack
Official PyTorch implementation of End-to-end 3D Tracking with Decoupled Queries [ICCV 2023]
☆63Updated last year
Alternatives and similar repositories for DQTrack:
Users that are interested in DQTrack are comparing it to the libraries listed below
- ☆77Updated 2 years ago
- ☆18Updated 2 years ago
- [CVPR 2023] Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark☆76Updated 2 years ago
- [ICCV 2023] GeoMIM: towards better 3d knowledge transfer via masked image modeling for multi-view 3d understanding☆47Updated last year
- ☆45Updated 2 years ago
- OpenAD: Open-World Autonomous Driving Benchmark for 3D Object Detection☆46Updated 3 months ago
- Code for MonoJSG: Joint Semantic and Geometric Cost Volume for Monocular 3D Object Detection☆31Updated 2 years ago
- [CVPR 2023] FrustumFormer: Adaptive Instance-aware Resampling for Multi-view 3D Detection☆30Updated 7 months ago
- [ECCV 2022] Learning Ego 3D Representation as Ray Tracing☆105Updated 2 years ago
- DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detection☆36Updated last year
- AeDet: Azimuth-invariant Multi-view 3D Object Detection, CVPR2023☆74Updated last year
- ☆76Updated last year
- Implementation of SimMOD: A Simple Baseline for Multi-Camera 3D Object Detection☆48Updated 2 years ago
- Toolkit to convert a clean LiDAR-camera dataset into a robustness benchmark☆57Updated 2 years ago
- Fully Sparse Transformer 3D Detector for LiDAR Point Cloud☆29Updated last year
- This is the implementation of the paper "SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection" (I…☆68Updated last year
- [IROS 2024]InverseMatrixVT3D: An Efficient Projection Matrix-Based Approach for 3D Occupancy Prediction☆27Updated 8 months ago
- Target Inner-Geometry Learning for BEV 3D Object Detection☆89Updated last year
- Repo of "MsSVT: Mixed-scale Sparse Voxel Transformer for 3D Object Detection on Point Clouds".☆39Updated last year
- [ECCV 2024] Occupancy as Set of Points☆89Updated 8 months ago
- This method performs 3D object detection in the BEV space using images from multiple cameras.☆32Updated 2 years ago
- ☆59Updated last year
- Multi-Modal 3D Object Detection by Box Matching☆53Updated last year
- [AAAI 2024] BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios☆57Updated 2 months ago
- The offical code of PolarBEV (CoRL2022).