This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

Awesome Monocular 3D detection

Source code for the ICCV 2023 paper: Robust Monocular Depth Estimation under Challenging Conditions

BEVDet implemented by TensorRT, C++； Achieving real-time performance on Orin

Official codebase for the paper 'Radar Enlighten the Dark: Enhancing Low-Visibility Perception for Automated Vehicles with Camera-Radar Fusion

Semantic Guided Depth Estimation with Transformers Using Monocular Camera and Sparse Radar

Radar-Camera Fusion Dense Prediction Transformer

TJ4DRadSet: A 4D Radar Dataset for Autonomous Driving

The first DETR-based monocular detector without additional depth supervision, anchors or NMS.

Rank 1st in the leaderboard of SemanticKITTI semantic segmentation (both single-scan and multi-scan) (Nov. 2020) (CVPR2021 Oral)

Official code for BEVDepth.

Official code base of the BEVDet series .

A curated list of radar datasets, detection, tracking and fusion

deep learning for image processing including classification and object-detection etc.

This is a program that fuses millimeter wave radar and camera information. At the same time, yolov4 is used for target detection.

Helper tools for the radar scenes data set.

Ros package to fuse image with cloud

Pytorch implementation of "Deep Ordinal Regression Network for Monocular Depth Estimation" paper by Fu et. al.