VPRzhou's repositories
OpenABLE
OpenABLE is an open toolbox that contributes different solutions and functionalities to the research community in the topic of life-long visual localization for autonomous vehicles. You can access to the Webpage of the OpenABLE project for more information about it.
OpenSeqSLAM2.0
OpenSeqSLAM2.0: An Open Source Toolbox for Visual Place Recognition Under Changing Conditions
Visual_SLAM_Related_Research
视觉(语义) SLAM 相关研究跟踪
AutoGAN
[ICCV 2019] "AutoGAN: Neural Architecture Search for Generative Adversarial Networks" by Xinyu Gong, Shiyu Chang, Yifan Jiang and Zhangyang Wang
c9-python-getting-started
Sample code for Channel 9 Python for Beginners course
contextdesc
Implementation of CVPR'19 paper (oral) - ContextDesc: Local Descriptor Augmentation with Cross-Modality Context
darknet
YOLOv4 - Neural Networks for Object Detection (Windows and Linux version of Darknet )
Darknet-2
AlexeyAB-DarkNet源码解析
darknet-3
darknet深度学习框架源码分析:详细中文注释,涵盖框架原理与实现语法分析
DBoW2
Enhanced hierarchical bag-of-word library for C++
DLfeature_PlaceRecog_icra2017
Dataset and official Caffe Implementation for learning a condition-robust feature representation for long-term visual localization
hfnet
From Coarse to Fine: Robust Hierarchical Localization at Large Scale with HF-Net (https://arxiv.org/abs/1812.03506)
IROS2017_OnlyLookOnce
This repository contains code for our IROS 2017 paper "Only look once, mining distinctive landmarks from convnet for visual place recognition" by Zetao Chen, Fabiola Maffra, Inkyu Sa, Margarita Chli
lf-net-release
Code Release for LF-Net: Learning Local Features from Images
models-1
Pre-trained and Reproduced Deep Learning Models (『飞桨』官方模型库,包含多种学术前沿和工业场景验证有效的领先模型)
Multi-Process-Fusion
Multi-Process Fusion: Visual Place Recognition Using Multiple Image Processing Methods
openslam_openseqslam
openseqslam repos from OpenSLAM.org
PaddleDetection
Object detection and instance segmentation toolkit based on PaddlePaddle.
pySeqSLAM
Python SeqSLAM - port of Niko Sünderhauf's OpenSeqSLAM for place recognition
S2DHM
Sparse-to-Dense Hypercolumn Matching for Long-Term Visual Localization
single-view-place-recognition
Single-View Place Recognition under Seasonal Changes (http://webdiis.unizar.es/~jmfacil/pr-nordland/)
tensorflow-yolov3
🔥 TensorFlow Code for technical report: "YOLOv3: An Incremental Improvement"
Yolo-Fastest
:zap: Yolo universal target detection model combined with EfficientNet-lite, the calculation amount is only 230Mflops(0.23Bflops), and the model size is 1.3MB
yolov3
YOLOv3 in PyTorch > ONNX > CoreML > TFLite