Computer Vision

Learn OpenCV in 4 Hours - Code used in my Python and OpenCV course on freeCodeCamp.

GPS-denied drone navigation layer: optical flow + offline map geo-match + EKF → MAVLink (sim-validated).

A Unified Toolkit for Deep Learning Based Document Image Analysis

A PyTorch Implementation of Single Shot MultiBox Detector

OpenPCDet Toolbox for LiDAR-based 3D Object Detection.

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

Accelerated deep learning R&D

Official code for Echo-Memory: a controlled study of memory in action-conditioned video world models (Context, Compression, Spatial, State-Space).

Jetson Nano with Ubuntu 20.04 image

FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)

Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

OpenMMLab's next-generation platform for general 3D object detection.

Fit compact primitive assemblies (SuperFrusta, cuboids, superquadrics) to 3D shapes via residual fitting. CVPR 2026.

Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.

[ICML 2026] ByteDance's All-in-One Video Generation Model for Human-Object Interaction Video Generation

深度学习面试宝典（含数学、机器学习、深度学习、计算机视觉、自然语言处理和SLAM等方向）

Official Code for ECCV 2026 paper "EgoExoMoCap: Distributed Ego-Exo Human Motion Capture"

A curated, learning-friendly list of egocentric (first-person) vision & embodied AI resources: papers, datasets, code, models, toolkits, challenges and tutorials, covering both classic foundational works and cutting-edge advances, catering to research initiation and industrial deployment.

Go package for computer vision using OpenCV 4 and beyond. Includes support for DNN, CUDA, OpenCV Contrib, and OpenVINO.

Camera-only closed-loop driving agent for Forza Horizon 6, with geometry as the control interface.

img2table is a table identification and extraction Python Library for PDF and images, based on OpenCV image processing

[ICLR 2023] Official implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection"

Official implementation of paper LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models

Image-to-image translation with conditional adversarial nets

Realtime human head pose estimation with ONNXRuntime and OpenCV.

Modular open-source brain for legged robots. Web UI for teleops, autonomous navigation, mapping & monitoring. 3D-printable hardware that runs on ROS2.

A simplified implemention of Faster R-CNN that replicate performance from origin paper

OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.

Fisheye or Normal Camera Intrinsic and Extrinsic Calibration. Surround Camera Bird Eye View Generator.

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

NEWTON: Agentic Planning for Physically Grounded Video Generation

AI算法岗求职攻略（涵盖准备攻略、刷题指南、内推和AI公司清单等资料）

An open source library and framework for deep learning on satellite and aerial imagery.

一款入门级的人脸、视频、文字检测以及识别的项目.

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

Model-agnostic state layer for world models — turn any detector (YOLO · VLM · DINO) into one standard, queryable stream of events + latent state. numpy-only, runs on CPU at the edge.

Remove backgrounds from images directly in the browser environment with ease and no additional costs or privacy concerns. Explore an interactive demo.

记录每天整理的计算机视觉/深度学习/机器学习相关方向的论文

:fire: :fire: :fire: A paper list of some recent Computer Vision(CV) works

TensorFlow 2.x version's Tutorials and Examples, including CNN, RNN, GAN, Auto-Encoders, FasterRCNN, GPT, BERT examples, etc. TF 2.0版入门实例代码，实战教程。

[Patterns (Cell subsidiary journal)] The official code for "UltraLight VM-UNet: Parallel Vision Mamba Significantly Reduces Parameters for Skin Lesion Segmentation".

Your new Mentor for Data Science E-Learning.

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

:alarm_clock: AI conference deadline countdowns

FASHN VTON v1.5: Efficient Maskless Virtual Try-On in Pixel Space

You Only Look Once for Panopitic Driving Perception.（MIR2022）

Single Shot MultiBox Detector in TensorFlow

Convert 2D videos and photos into interactive 3D scenes using Gaussian splatting backends (VGGT, LongSplat, DepthSplat, SHARP, TripoSplat), Rerun, and the SuperSplat editor.

Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image Matting, 3D Segmentation, etc.

Virtually controlling computer using hand-gestures and voice commands. Using MediaPipe, OpenCV Python.