CV
机器视觉
最后更新于
这有帮助吗？
这张计算机界最流行的图像，为什么成了学术期刊不敢碰的禁忌？ 量子位
faceai 一款入门级的人脸、视频、文字检测以及识别的项目
[Tutorialsplanet.NET] Udemy - Deep Learning and Computer Vision A-Z™ OpenCV, SSD & GANs
pip install mediapipe
import mediapipe as mp
pip install opencv-python
import cv2
Public LIVE: Code Walkthrough (OpenCV using Python)
LEARN OPENCV C++ in 4 HOURS | Including 3x Example Projects Win/Mac (2021)
OpenCV实现视频拼接（书童）
สอน Python & OpenCV Image Processing เบื้องต้น (2 ชั่วโมงเต็ม!)
How to detect DeepFakes with MesoNet | 20 MIN. PYTHON TUTORIAL
视频格式, 封装格式, 编码格式, h.264 编码 mp4 封装
封装格式 mp4
视频编码 h.264
帧内压缩 intraframe jpeg 保留亮度 压缩颜色 缩小90%
帧间压缩 interframe 关键帧+细节变化 I帧、P帧和B帧
adobe media encoder
码率, 控制码率的方法, 恒定码率cbr 可变码率vbr 固定质量crf 比特率
16mbps 16mb/s 5000kbps
cpu画质预设 fast
300mbps ->3mbps MediaCoder x64
显卡编码 nvenc编码器 直播用
avisynth.nl AVS的各种用法 doom9论坛（forum.doom9.org）有用的压制技巧
h.265 hevc B站的视频上传规范
obs studio
CodeFormer JavPlayer JavPlayerfree(假) TecoGAN JavPlayer中文交流论坛 SD:BVPP模型
dino-self-supervised-learning-demo
Basic OCR bill detection system | Pytesseract | Python | Data Analysis Cherry’s Project
视错觉通常是由于视觉系统对来自外界的信息进行处理时发生的。视觉系统是一个复杂的系统，它包括眼睛、神经、大脑皮层等多个组成部分。当光线进入眼睛并刺激视网膜时，视觉系统开始对外界信息进行处理和解释。
视错觉通常是由于视觉系统处理信息时出现了一些偏差或错误所导致的。例如，视觉系统可能会将来自外界的信息解释为具有不同的深度、大小、形状、颜色或运动状态，这可能导致视错觉的发生。此外，环境因素，如光线、对比度、背景等也可能会影响视觉系统的处理和解释。
另外，一些视错觉可能是由于人类视觉系统中特定神经机制的工作方式所致。例如，当视觉系统处理来自不同位置的信息时，可能会产生尺度错觉。这是因为视觉系统在将来自不同位置的信息整合在一起时，可能会出现某些细节信息的缺失或模糊，导致我们产生了不正确的大小感知。
总之，视错觉的发生是由于视觉系统在处理外界信息时出现了偏差或错误所导致的，这可能是由多种因素造成的。研究视错觉可以帮助我们更好地了解人类视觉系统的工作原理，并提高我们对视觉信息的处理和解释的准确性。
三角形分割错觉, Triangle division illusion
艾宾浩斯错觉, Ebginghaus illusion
赫曼方格错觉, Hermann's lattice illusion
康士维错觉, Canway illusion
方向对比错觉, Direction contrast illusion
米勒-莱尔错觉, Miller-Lyle illusion
同时对比错觉, Simultaneous illusion
对齐对比错觉, Contrast illusion
amd fsr
Supervisely(, )
ComputerVisionFoundation Videos(, )
ROBOTFIST
Raúl Mur Artal(, )
小无敌技术讲堂(, )
Denis Dmitriev(, )
Murtaza's Workshop - Robotics and AI(, )
Jeremy Howard
Apeer_micro
James Briggs
恩培 抖音号：
AINTU-人工智慧技術暨全幅健康照護聯合研究中心
Computer vision engineer
Find Interesting AI
李飞飞: 我们怎么教计算机理解图片？
MAE 论文逐段精读【论文精读】
How computers learn to recognize objects instantly | Joseph Redmon
机器视觉-2020北邮远程课
CS 198-126: Modern Computer Vision Fall 2022 (UC Berkeley)
CS231n Winter 2016(, )
CS231N-2016 2017 Stanford University School of Engineering
圖象處理編程知識 | 如何為圖象去除Alpha透明通道？網上廣傳的方法是錯的，小心！
Convolutional Neural Networks for Visual Recognition - Fei Fei Li | Stanford University
Fei-Fei Li & Demis Hassabis: Using AI to Accelerate Scientific Discovery
Full Stack Computer Vision Tutorial with Tensorflow, Python ()
曲线高级用法【】08:10
遥感数字图像处理-朱文泉（北京师范大学）
Image Analysis in Python with SciPy and scikit-image | | Stefan van der Walt
Cmputer Vision
Deep Learning for Computer Vision
Deep Learning for Computer Vision
Build An Image Editor in HTML CSS & JavaScript | Image Editor in JavaScript
图像处理与分析 武汉大学 贾永红 共41课时 6小时4分9秒
数字图像处理 天津理工大学 共49课时 1天4小时20分39秒
天津理工大学-数字图像处理（国家级精品课）
Advanced Computer Vision with Python - Full Course 6：40：40
Images
RGB Colour Mixer Application
Introduction to Computer Vision |
Why do computers use RGB for colors, and not RBY?
Python tutorials for image processing and machine learning
Introductory python tutorials for image processing
Image Annotation for Machine Learning
The Unreasonable Effectiveness of JPEG: A Signal Processing Approach
How PNG Works: Compromising Speed for Quality
Huffman Codes: An Information Theory Perspective
Image processing with python
Image filters in python
Python tutorials for image processing and machine learning
Hyperspectral Image Processing 高光谱图像处理
Fun Python Exercise - Convert Numbers to Images with NumPy, OpenCV and Pillow
网络视频监控技术-任帅（长安大学）
Image Localization: Explanation + Code in TensorFlow (And how to make Multi-Output Models!)
Introduction to SIFT (Scale-Invariant Feature Transform)
Computer Vision
Computer Vision Tutorial
Introduction to AI & Neural Networks
AI 產業訓練課程
Vision Transformers (ViT) Explained + Fine-tuning in Python
AI Image Manipulation
Mediapipe
一小时学习python和mediapipe
利用MMediapipe和DGL实现火影结印识别与追踪---特殊手势识别
恩培 抖音号：
AI Face Body and Hand Pose Detection with Python and Mediapipe
Latest 3D OBJECT DETECTION with 30+ FPS on CPU - MediaPipe and OpenCV Python
MediaPipe - AI机器学习套件介绍
【python】OpenCV + MediaPipe 手部追踪 ｜
Exercise Rep Counter using OpenCV | Python | Computer Vision | Machine Learning
Push-up counter using Mediapipe python
OpenCVTutorials(, )
doc OpenCV-Python Tutorials
OpenCV-Python Tutorials
Introduction to OpenCV-Python Tutorials
OpenCV Python Course - Learn Computer Vision and AI
ProgrammingKnowledge
linuxhint
Image Processing - OpenCV and Matlab - Training | Projects -
OpenCV基础入门
OpenCV with Python for Image and Video Analysis
Computer Vision - OpenCV
Android Development with OpenCV
教程 Python 和 OpenCV 图像处理基础（2 小时！）
【python】opencv 2小时初学者教程
OpenCV 3.4 with Python 3 Tutorial
Images Comparison with Opencv and Python
Gaze controlled keyboard with Opencv and Python
Neural Networks from Scratch with Python and Opencv
OpenCV Course - Full Tutorial with Python
OpenCV视觉处理核心课程
影像處理
Hand Distance Measurement with Normal Webcam + Game | OpenCV Python
35行python代码100万？人工智能光速入门
Using OpenCV with MFC
OpenCV and Python
OpenCV Python Tutorials
OpenCV
Python Open CV
OpenCV and Python Projects
HALCON Tutorials
将门创投 | 微软亚洲研究院胡瀚：图像识别中的非网格化网络
Multi Class Image Classification
Leaf Disease Classification Using PyTorch
3D Image Classification from CT Scans - Keras Code Examples
OpenAI's CLIP for Zero Shot Image Classification
Fast Zero Shot Object Detection with OpenAI CLIP
Image classification from scratch - Keras Code Examples
Image classification with Python and Scikit learn | Computer vision tutorial
Image Classification with Neural Networks in Python
Build a Deep CNN Image Classifier with ANY Images
How AI Image Generators Work (Stable Diffusion / Dall-E) -
AI绘画系列
AI Generated Images Are Getting Too Real
Anime Related AI Applications
Adobe Firefly
史上最强AI画图软件PS AI中文版、永久免费使用！Win+Mac系统、附安装流程和疑难杂症解决！
Turn Midjourney Illustration to Vector in Figma
新的 AI 繪圖工具抵達戰場！！Leonardo.ai 五個超酷功能讓 Midjourney 也感到害怕
Ai绘图谁更强？ 16GB VS 22GB
2080Ti所有涡轮卡都是这么改的！
Midjourney教程 入门到精通
AIGC、ChatGPT、MidJourney
DDPM - Diffusion Models Beat GANs on Image Synthesis (Machine Learning Research Paper Explained)
最真实人工智能换脸--AI换脸背后的秘密（deepfacelab操作指南）
iperov/
AI 换脸教程 - 最简单易懂的 Faceswap 换脸视频！完全免费开源 2022 |
iperov/ creating deepfakes
Deepfacelab智能换脸
Age & Gender Prediction with DeepFace in Python
【公众号：马哥随笔】AI视频换脸！史上最强最快的方法，100%成功，完全免费，无需配置、打开即用、使用操作简单 git
How To Create Deepfake
runway text 2 video
This New AI Is The Future of Videomaking!
HeyGen AI-powered video creations at scale
t04glovern/
Talk | 威斯康星大学麦迪逊分校穆方舟：3D相片的风格化-从单张输入图生成风格化的全新视角
AI Caricatures And Portrait Style Transfer Are Here!
【AIGC】谷歌公开StyleDrop模型论文 | 图像风格定制大师 | LOGO也能轻松生成 | 挑战Midjourney | 基于Muse模型
Image Compression Using PCA in Python
Talk | 商汤科技计算机视觉研究员何岱岚：基于深度学习的高效图像压缩编码
JPEG 有损压缩 离散余弦变换 DCT 一条视频讲清楚
ZIP压缩算法刨析 什么是LZ77编码
哈夫曼编码很难懂？一条视频讲清楚
How JPEG Works
How are Images Compressed? [46MB ↘↘ 4.07MB] JPEG In Depth
如何压缩视频，把文件变小，还没画质损失？
完全解析：视频编码与封装
高画质的背后——视频的封装与编码
【科普】“视频”是怎么来的？H.264、码率这些词又是什么意思？
【科普】手把手教你做直播！4K直播了解一下？
Depix
利用AI给黑白照片上色
CodeFormer-GUI 零度解说
DeblurGAN 除去运动模糊
ShieldMnt/
生成式填充和扩图又一替代方案！Topaz Photo AI。
csxmli2016/
CVPR2021论文能修复马赛克？香港理工大学新研究，修复模糊图像！
GAN Prior Embedded Network for Blind Face Restoration in the Wild
Towards Real-World Blind Face Restoration with Generative Facial Prior
TecoGAN
SixQuant/ 去除图片中的水印
?q=cnn-watermark-removal
Deep Image Prior paper git
模糊视频秒变高清！ Chrome、Edge浏览器可直接开启，AI又添全新“VSR”超分辨率技术，支持三代N卡、A卡 |
Justin62628/ Squirrel Anime Enhance
xinntao/ Enhanced SRGAN
AI技術去除馬賽克，全民步兵時代已經來臨
现在AI这么强，能去马赛克吗？#技术 #科技 #知识 #黑科技 #涨知识
facebookresearch/
通过截图找片子！好多人在寻找的搜索方法！|
gettyimages
Pinecone Demo - Image similarity search example
Image Similarity Search using PyTorch & Spotify
Google Image
Kernel Size and Why Everyone Loves 3x3 - Neural Network Convolution
What are Convolutional Neural Networks (CNNs)?
What is a convolutional neural network (CNN)?
What is CNN Convolutional neural network | Why should we use CNN | Goeduhub
CNN architecture in 5 minutes - A Quick Learning
Convolutional Neural Networks | CNN | Kernel | Stride | Padding | Pooling | Flatten | Formula
Convolutional Neural Networks
Convolutional Neural Networks Explained (CNN Visualized)
Convolutional Neural Network Visualization by Otavio Good
2D Convolution Neural Network Animation
Convolutional Neural Networks (CNNs) explained
卷积神经网络的简介（ML Zero to Hero，第三集）
【機器學習2021】卷積神經網路 (Convolutional Neural Networks, CNN)
AlexNet论文逐段精读
Convolution Neural Networks
Convolutional Neural Networks in Practice // Cassidy Williams, Clarifai (FirstMark's Code Driven)
CNN Explainer
Why do Convolutional Neural Networks work so well?
撑起计算机视觉半边天的ResNet
ResNet论文逐段精读
EfficientNet Explained!
EfficientNet! - Keras Code Examples
EfficientNet Explained: Rethinking Model Scaling for Convolutional Neural Networks
EfficientNet Paper Walkthrough
EfficientNet from scratch in Pytorch
Detectron2(, , )
MaskRcnn-benchmark(, )
图像分割算法实战(深度学习) 唐宇迪
面向医学领域的深度学习项目实战 唐宇迪
73 - Image Segmentation using U-Net - Part1 (What is U-net?)
Image Matting
Jiake Xie 谢家柯
picup
U-net for image segmentation
280 - Custom object segmentation using StarDist library in python
3D MRI brain segmentation - Made with TensorFlow.js
PyTorch Image Segmentation Tutorial with U-NET: everything from scratch baby
I tried building an ML Cancer Segmentation API in 15 Minutes
AI 图片去背景工具，可离线，终身免费，同时支持 Windows 和 Linux
facebookresearch/
【人工智能】Meta发布史上最强抠图模型 | Segment Anything Model | 零样本学习可分割一切物体 | 计算机视觉迎来GPT-3时刻
307 - Segment your images in python without training using Segment Anything Model (SAM)
Advancing the state of the art in computer vision with self-supervised Transformers and 10x more efficient training
Explore Meta AI’s self-supervised learning demo for images
DINO: Emerging Properties in Self-Supervised Vision Transformers Summary
DINOv2: State-of-the-art computer vision models with self-supervised learning
facebookresearch/
facebookresearch/ DINO2 API documentation 4:00
DINOv2 from Meta AI: Data pipeline, model training and results explained
Tensorflow Object Detection in 5 Hours with Python | Full Course with 3 Projects()
I tried building a Computer Vision Game in 12 Hours
【AI Meetup】 最強的AI物件偵測技術Yolo-v4作者親自剖析
What is YOLO algorithm? | Deep Learning Tutorial 31 (Tensorflow, Keras & Python)
Object detection using YOLO v4 and pre trained model | Deep Learning Tutorial 32 (Tensorflow)
facebookresearch/Detectron
YOLOv5发布v6.0版本，看看效果怎么样
Streamlit部署YOLOv5目标检测
YOLO
Build a Deep Face Detection Model with Python and Tensorflow | Full Course
Gilbert Tanner
【论文推荐】《目标检测》必看的8篇论文【附pdf】
Facebook DETR | ML Coding Series | End to end object detection with transformers
使用樹莓派及桌上型電腦進行實時物體偵測
目标检测的关系网络
283 - What is Mask R-CNN?
284 - Installing Mask RCNN and troubleshooting errors
286 - Object detection using Mask RCNN: end-to-end from annotation to prediction
Mask RCNN
只要你在社交平台发了照片，这个AI就能利用开放式摄像头找到你摆拍的全过程
Coding an Object Detection App in 15 mins
DETR: End-to-End Object Detection with Transformers (Paper Explained)
2 Faster R-CNN Architecture
YOLO For Smart Object Detection Using Python | Project For Beginners
Lane detection and object detection with OpenCV & TensorFlow
YOLOv8 影像分析演算法實作教學影片：不需錨點，可進行影像分類、物件偵測、及物件分割
Complete YOLO v8 Custom Object Detection Tutorial | Windows & Linux
YOLOv8 COMPLETE Tutorial | Object Detection | Segmentation | Classification
Instance segmentation YOLO v8 | Opencv with Python tutorial
Train Yolov8 object detection on a custom dataset | Step by step guide | Computer vision tutorial
Aladdin Persson
Talk | 阿里巴巴达摩院算法工程师许贤哲：DAMO-YOLO：兼顾速度与精度的高效目标检测框架
Building a Cat Detector with LandingLens
Object Detection (Yolov8, YOLOv7, YOLOv3, YOLOv4 , TensorFlow)
Detectron2 Instance Segmentation and Object Detection
Realtime Object Detection Android App | Kotlin | Camera2 api | tflite
Object Tracking with Opencv and Python
Talk | 香港中文大学（深圳）计算机信息工程在读博士生郑超达：以运动为导向的点云单目标跟踪
Object Tracking from scratch with OpenCV and Python
Tricking AI Image Recognition -
YOLOv5 的 Android 部署，基于 tflite
I Built an AI That Shoots Me in the Face When I Get Distracted
Tracking Cars with Drones and LandingLens
手把手带你实战YOLOv5
【人工智能】Segment-and-Track Anything | SAM-Track | 视频版SAM来了，分割/跟踪/编辑一切 | 现已开源 | 浙江大学计算机学院ReLER实验室
Involution: Inverting the Inherence of Convolution for Visual Recognition (Research Paper Explained)
Gesture Volume Control | OpenCV Python 2021 |
Hand Tracking 30 FPS using CPU | OpenCV Python (2021) | Computer Vision
Create a Rock Paper Scissors AI | Keras and OpenCV | Tutorial | Python
Mouse Control using OpenCV and a Webcam
facebookresearch/InterHand2.6M
Sign Language Detection using ACTION RECOGNITION with Python | LSTM Deep Learning Model
Detect 468 Face Landmarks in Real-time()
ProgrammingKnowledge
Eyes Tracking Opencv python
机器学习入门
人脸识别的基本原理
动手实现人脸关键点识别
Simple Face Detection in Python
Build a Deep Face Detection Model with Python and Tensorflow | Full Course
人脸识别啥原理？人工智能（二）卷积神经网络
CrazyTalk第七课 头像创建 CrazyTalk8教程人脸识别验证教程照片变动画人脸五官编辑裁剪静态照片修改动态
QQ丨支付宝丨交易猫丨淘宝丨平台实名验证，简单做人脸视频教程，原理说明，通用模板。人脸识别验证，人脸实名技术，支付宝实名，QQ过人脸教程。
人脸对齐(Face Alignment) - MSQRD, Snow, Snapchat的原理 - 上
Face Alignment - How MSQRD, Snow, Snapchat works - Part 2/2
Python Computer Vision OpenCV - Find Face Landmarks using DLIB
Pose Estimation
3D Motion Capture using Normal Webcam | Computer Vision OpenCV
Track Human Activity Using Scikit Learn | Python | Tutorial For Beginners
DAVAR-OCR
MASTER: Multi-Aspect Non-local Network for Scene Text Recognition
Extract Text From Images in Python (OCR) Tesseract
Optical Character Recognition (OCR) -
How Does Optical Character Recognition (OCR) Work?
Automatic OCR Receipt & Invoice Parsing in Python
Extract Text From Images in Python (OCR)
Optical Character Recognition Project | Find Text inside the images/Videos Machine Learning | OCR
Optical Character Recognition From Beginner to Expert Using Python | Tesseract - Complete Tutorial
Automatic Number Plate Recognition using Tensorflow and EasyOCR Full Course in 2 Hours | Python
OCR技术总结
[表格识别论文解读]Deep Splitting and Merging for Table Structure Decomposition
视觉时-空注意力建模与学习
第4集 | 神奇的视觉差，你还相信你的眼睛吗？#视错觉#板式设计#平面设计#视觉差#视觉艺术#ui设计#视错觉小课堂
測試一下你對速度的感知到底怎麼樣 |
SwinIR: Image Restoration Using Swin Transformer
基于深度学习和行人重识别(, )
Person_reID_baseline_pytorch(, )
3D Point Cloud Classification in Python - PointNet Concept and Implementation
中科院自动化所在读博士刘永成：深度学习在3D点云处理中的探索
Talk | 牛津大学胡庆拥：大场景三维点云语义理解Ⅱ
将门创投 | 斯坦福大学在读博士生祁芮中台：点云上的深度学习及其在三维场景理解中的应用
3D Deep Learning Tutorial
Instant Neural Graphics Primitives 能够将 2D 图像转 3D 模型
英伟达新技术训练NeRF模型
Como instalar NERF en Windows + Tutorial + Ejemplos + Recomendaciones
NeRF (Neural Radiance Fields)
BARF 🤮: Bundle-Adjusting Neural Radiance Fields (ICCV 2021 oral)
Google’s New AI: Fly INTO Photos! 🐦
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis (ML Research Paper Explained)
Talk | 香港中文大学MMLab在读博士生徐英豪：通过结构和纹理表示实现3D图像合成
Talk | AAAI'23 Oral 北京大学陈嘉毅：自然条件下基于三维点云的手物联合位姿追踪与重建
【怜狸酱的小课堂】使用百度AI studio进行视频插帧
【硬件科普】免费提升画质和帧数？详解DLSS2.0的工作原理与作用 抗锯齿
【GPU】NVIDIA RTX40專有技術，DLSS3.0技術解析！
DLSS 3 RTX4090：性能新标杆，不只是打游戏
【Huan】 無庸置疑的強大。 NVIDIA GeForce RTX 4090性能實測
RTX 50系显卡来了！NV有哪些干货？
【】 該不會又是接下來的幾年沒對手了吧..? NVIDIA GeForce RTX 5090創始版性能實測
I3D 论文精读【论文精读】
双流网络论文逐段精读【论文精读】
Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos (Paper Explained)
Talk | 香港大学在读博士生马逴凡：重新思考分辨率对于高效视频理解的意义
ClarityCoders
Learn Code By Gaming
Know-How
【亦】警惕AI外挂！我写了一个枪枪爆头的视觉AI，又亲手“杀死”了它
OpenCV Object Detection in Games
I tried to make a Valorant AI using computer vision
AI游戏脚本难不难学，竞技类MOBA链游有没有机会搬砖打金？
Making a Whack a Mole bot using OpenCV's Match Template
Make a bot that plays chrome dino game in python | OpenCV Tutorial | Beginners
Dominating an Online Multiplayer Game using Python and OpenCV.
TensorFlow CS:GO custom object detection aim bot
Unity 3D Augmented Reality Application With OpenCV and Python
Computer Vision With Arduino | 2 Hour Course | OpenCV Python
图片缩放.py
This Image is Made of Text
Fingerprint Matching in Python 指纹识别
NVIDIA Instant Neural Graphics Primitives (nerf)
OlafenwaMoses/ A python library
Coding Challenge: Image to ASCII
AI辅助设计