[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.

✔️李沐 【动手学深度学习】课程学习笔记：使用pycharm编程，基于pytorch框架实现。

记录cv算法工程师的成长之路，分享计算机视觉和模型压缩部署技术栈笔记。https://harleyszhang.github.io/cv_note/

The devkit of the nuScenes dataset.

[PAMI'23] TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving; [CVPR'21] Multi-Modal Fusion Transformer for End-to-End Autonomous Driving

Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D (ECCV 2020)

[ECCV2022] PETR: Position Embedding Transformation for Multi-View 3D Object Detection & [ICCV2023] PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images

[ICCV 2023] StreamPETR: Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection

深度学习系统笔记，包含深度学习数学基础知识、神经网络基础部件详解、深度学习炼丹策略、模型压缩算法详解。

Sparse4D v1 & v2

[ICCV 2023] SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos

[ICCV 2023] The first DETR model for monocular 3D object detection with depth-guided transformer

[ECCV 2022] ST-P3, an end-to-end vision-based autonomous driving framework via spatial-temporal feature learning.

This project aims to provide a data and control bridge for the communication between the latest version of Apollo and Carla.

[CVPR2024] Official Repository of Paper "Panacea: Panoramic and Controllable Video Generation for Autonomous Driving"

[IROS 2024 Oral Presentation] WidthFormer: Toward Efficient Transformer-based BEV View Transformation

MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer (CVPR 2022)

[ECCV 2024] Ray Denoising (RayDN): Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection

[ECCV 2024] OPEN: Object-wise Position Embedding for Multi-view 3D Object Detection

[ECCV2024] UniM2AE: Multi-modal Masked Autoencoders with Unified 3D Representation for 3D Perception in Autonomous Driving

StreamPETR with 3dppe Extension

Generate nuScenes style birdeye-view image in Carla Simulator

Enhancing 3D Object Detection with 2D Detection-Guided Query Anchors, CVPR 2024

The reproduction project of the BEV model # StreamPETR, which includes some code annotation work

一个nuscenes格式的carla虚拟仿真数据收集程序，用于收集复眼结构下的3D目标检测数据集 A carla virtual simulation data collection program in nuscenes format Used to collect 3D target detection datasets under compound eye structures