Hale423 / bev_align_pluginLinks
A plugin to make view transformer from perspective view to bird-eye-view, it is used in bevdet
☆24Updated 2 years ago
Alternatives and similar repositories for bev_align_plugin
Users that are interested in bev_align_plugin are comparing it to the libraries listed below
Sorting:
- DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets(CVPR2023),vaymo vehicle 3D Object Detection(top2), waymo cyclist 3D Object Detec…☆87Updated 2 years ago
- CenterPoint model trained with MMDetection3d on custom dataset, and deployed with TensorRT☆35Updated 2 years ago
- ☆37Updated last year
- [ICLR2024]: LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection.☆79Updated last year
- [IROS 2024 Oral Presentation] WidthFormer: Toward Efficient Transformer-based BEV View Transformation☆155Updated 7 months ago
- ☆45Updated 3 months ago
- ☆33Updated 2 months ago
- Official code for MatrixVT on BEVDepth.☆46Updated 2 years ago
- FastPillars: A Deployment-friendly Pillar-based 3D Detector☆167Updated 10 months ago
- ☆75Updated 11 months ago
- ☆23Updated last year
- ☆30Updated 3 years ago
- [3DV 2025] LSSInst: Improving Geometric Modeling in LSS-Based BEV Perception with Instance Representation☆19Updated last month
- ☆29Updated 2 years ago
- ☆109Updated 3 years ago
- Implemented BEVFormer support for BEV segmentation☆150Updated 2 years ago
- 3d object detection model smoke c++ inference code☆37Updated 2 years ago
- A fork of the BEVDet series .☆21Updated 2 years ago
- easy and simple way to train, export and deploy pointpillars for 3D detection☆62Updated 4 years ago
- BEVDet online real-time inference using CUDA, TensorRT, ROS1 & C++.☆112Updated last year
- An official code release of our CVPR'23 paper, BEVHeight☆223Updated last year
- End2EndPerception deployment solution based on vision sparse transformer paradigm is open sourced.☆157Updated 10 months ago
- An official code release of BEVHeight++☆37Updated 9 months ago
- POWERBEV, a novel and elegant vision-based end-to-end framework that only consists of 2D convolutional layers to perform perception and f…☆96Updated last year
- ☆33Updated 5 years ago
- (ECCV2024)ADMap: Anti-disturbance framework for reconstructing online vectorized HD map☆77Updated last year
- This repository is an official implementation of HVDetFusion☆77Updated 2 years ago
- NuScenes-like evaluation code for 3D bounding boxes.☆31Updated 2 years ago
- ☆56Updated last year
- Add some features to yolox☆19Updated 2 years ago