1018365842

3DDFA

The PyTorch improved version of TPAMI 2017 paper: Face Alignment in Full Pose Range: A 3D Total Solution.

awesome-lane-detection

A paper list of lane detection.

awesomeCV

paper reading note

Camera-lidar-joint-calibration

A sample way to jointly calibrate camera and lidar

CelebAMask-HQ

A large-scale face dataset for face parsing, recognition, generation and editing.

cvat

Powerful and efficient Computer Vision Annotion Tool (CVAT)

DeepInteractiveSegmentation

Getting to 99% Accuracy in Interactive Segmentation and Interactive Training and Architecture for Deep Object Selection

External-Attention-pytorch

🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

Far3D

[AAAI2024] Far3D: Expanding the Horizon for Surround-view 3D Object Detection

FusionLane

The source code of paper FusionLane

Hierarchical-Localization

Visual localization made easy with hloc

HyperFT

移动端快速视频人脸跟踪-移动端150FPS+

imu_utils

A ROS package tool to analyze the IMU performance.

JointCalib

light-LPR

Light-LPR是一个瞄准可以在嵌入式设备、手机端和普通的x86平台上运行的车牌识别开源项目，旨在支持各种场景的车牌识别,车牌字符识别准确率超99.95%，综合识别准确率超过99%，支持目前国内所有的车牌识别，觉得好用的一定要加星哦。

LVI-SAM

LVI-SAM: Tightly-coupled Lidar-Visual-Inertial Odometry via Smoothing and Mapping

MaskInsightface

基于人脸关键区域提取的人脸识别（LFW:99.82%+ CFP_FP:98.50%+ AgeDB30:98.25%+）

MVision

机器人视觉 移动机器人 VS-SLAM ORB-SLAM2 深度学习目标检测 yolov3 行为检测 opencv PCL 机器学习 无人驾驶

PatchMatchStereo

PatchMatchStereo立体匹配算法完整实现，代码规范，注释丰富且清晰，CSDN同步教学

PETR

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

PFLD

Implementation of PFLD A Practical Facial Landmark Detector , reference to https://arxiv.org/pdf/1902.10859.pdf

RetinaFace-Cpp

RetinaFace detector with C++

SemiGlobalMatching

SGM双目立体匹配算法完整实现，代码规范，注释丰富且清晰，CSDN同步教学

Silent-Face-Anti-Spoofing

静默活体检测（Silent-Face-Anti-Spoofing）

StreamPETR

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

tartanair_tools

TartanAir dataset tools and samples

Ultra-Light-Fast-Generic-Face-Detector-1MB

💎 一款超轻量级通用人脸检测模型（模型文件大小仅1MB，320x240输入下计算量仅90MFlops）适用于边缘计算设备、移动端设备以及PC

unrealcv

UnrealCV: Connecting Computer Vision to Unreal Engine

vins-mono-self-improved-

an improved version of vins-mono

X-PostProcessing-Library

XPL : High Quality Post Processing Effects Library For Unity