A PyTorch implementation of 'Deep Bilateral Learning for Real-Time Image Enhancement'

Dear ImGui: Bloat-free Graphical User interface for C++ with minimal dependencies

Set of methods to ensemble boxes from different object detection models, including implementation of "Weighted boxes fusion (WBF)" method.

Implementation of paper "DeepTag: A General Framework for Fiducial Marker Design and Detection"

This repository is used for automatic calibration between high resolution LiDAR and camera in targetless scenes.

Python and C++ implementation of "MarkerPose: Robust real-time planar target tracking for accurate stereo pose estimation". Accepted at LXCV Workshop @ CVPR 2021.

Camera self-calibration using vanishing point method.

Camera Intrinsic Calibration from a Single Image

Aruco marker detector and pose estimation for AR and Robotics with ROS support

🏀 Judging basketball shots and analyzing shooting pose with machine learning

Code for "RISA-Net: Rotation-Invariant and Structure-Aware Network for Fine-grained 3D Shape Retrieval"

🕶 A curated list of Tiny Object Detection papers and related resources.

🖍️ LabelImg is a graphical image annotation tool and label object bounding boxes in images

normal, fisheye, mono, stereo camera calibration

Minimal PyTorch implementation of YOLOv4

《机器学习》（西瓜书）公式推导解析，在线阅读地址：https://datawhalechina.github.io/pumpkin-book

(BMVC 2019) PyTorch implementation of Paper "Pose from Shape: Deep Pose Estimation for Arbitrary 3D Objects"

深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系[email protected] 版权所有，违权必究 Tan 2018.06

PyTorch Tutorial for Deep Learning Researchers

Hardnet descriptor model - "Working hard to know your neighbor's margins: Local descriptor learning loss"

Matrix Calculus via Differentials, Matrix Derivative, 矩阵求导方法

🚂 12306 购票助手，支持分布式，多账号，多任务购票以及 Web 页面管理

Models and Loss functions for our Mixed Classification-Regression framework for 3D Pose Estimation

LabelFusion: A Pipeline for Generating Ground Truth Labels for Real RGBD Data of Cluttered Scenes