Awesome Easy-to-Use Deep Time Series Modeling based on PaddlePaddle, including comprehensive functionality modules like TSDataset, Analysis, Transform, Models, AutoTS, and Ensemble, etc., supportin…

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…

Using ch_PP-OCRv4 model with tensorrt

Minimal code for Tapir model inference in Pytorch

MFT: Long-Term Tracking of Every Pixel -- code for the WACV 2024 paper

The C++ Implementation of XFeat (Accelerated Features).

[CVPR'24] LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry

xfeat for cpp

ONNX models of YOLO-World (an open-vocabulary object detection).

图像images/点云point clouds标注工具汇总

PointCloud Annotation Tools, support to label object bound box, ground, lane and kerb

[ECCV2024 Oral] SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow

Training YOLOv5/YOLOv9 to detect fire in a video

C++ implementation of ALIKED feature extractor with LightGlue kepoints matcher

YOLOv10: Real-Time End-to-End Object Detection

Implementing c++ inference for various learning point features

Project a PCD file to image

Panorama stitching based on asymmetric bidirectional optical flow

inplement some basic image processing algorithms

TensorRT deployment(C++) for paper "RAFT: Recurrent All-Pairs Field Transforms for Optical Flow"

Train and test image anomaly detection models with Anomalib. Examples on a custom dataset

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

🚀🚀🚀This is an AI high-performance reasoning C++ library, Currently supports the deployment of yolov5, yolov7, yolov7-pose, yolov8, yolov8-seg, yolov8-pose, yolov8-obb, yolox, RTDETR, DETR, depth-an…

TensorRT depth-anything for anyone and anywhere