lhwcv's repositories
DewarpNet
Code for the paper "DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks" (ICCV '19)
carmen_lcad
Version of the carmen robot framework developed by LCAD for IARA - Intelligent Autonomous Robotic Autonomobile.
Image-OutPainting
🏖 Keras Implementation of Painting outside the box
DocProj
Document Rectification and Illumination Correction using a Patch-based CNN
YOLOv3-model-pruning
在 oxford hand 数据集上对 YOLOv3 做模型剪枝（network slimming）
CHINESE-OCR-1
[python3.6] 运用tf实现自然场景文字检测,keras/pytorch实现ctpn+crnn+ctc实现不定长场景文字OCR识别
afm_cvpr2019
Official implementation of paper "Learning Attraction Field Map for Robust Line Segment Detection" (CVPR 2019)
cvpr2019
cvpr2019 papers，极市团队整理
deep_learning_object_detection
A paper list of object detection using deep learning.
ScanShine
ScanShine - quickly take shining scans of your documents by using only your android phone. This scanner app takes pictures of docs, trims, enhances, and let you share them to your friends. Everything packed in an optimistic sunshine theme.
SignatureVerificationDemo
Android 使用jni校验应用签名sha1值，防止so文件逆向盗用
python_web_Crawler_DA_ML_DL
python从最基础的语法历经网络基础、前端基础、后端基础和爬虫与数据基础走向机器学习
Fast_Portrait_Segmentation
Fast (aimed to "real time") Portrait Segmentation on mobile phone
content-preserving-tone-adjustment-for-image-enhancement
Image Enhancement Competition - NTIRE19 - CVPR19
rsgunet_image_enhance
Champion solution of the PIRM2018 Challenge on Perceptual Image Enhancement on Smartphones (Track B: Image Enhancement)
MORAN_v2
MORAN: A Multi-Object Rectified Attention Network for Scene Text Recognition
SRE_benchmark
Speaker recognition benchmark
cloud_german_rank10
Alibaba Cloud German rank10 baseline
siamese-triplet
Siamese and triplet networks with online pair/triplet mining in PyTorch
LineSegmentsDetection
:monkey:A collection of line segments detection algorithms.
maskrcnn-benchmark
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
hed-tutorial-for-document-scanning
Document Scanning With TensorFlow And OpenCV
notes
笔记
Image-Contrast-Enhancement
Python implementation of "A New Image Contrast Enhancement Algorithm Using Exposure Fusion Framework", CAIP2017
daily-paper-computer-vision
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
voice-vector
A deep neural network for finding text-independent speaker embedding written in tensorflow
awesome-speech-recognition-speech-synthesis-papers
Automatic Speech Recognition, Speaker Verification, Speech Synthesis, Language Modeling
deepgaze
Computer Vision library for human-computer interaction. It implements Head Pose and Gaze Direction Estimation Using Convolutional Neural Networks, Skin Detection through Backprojection, Motion Detection and Tracking, Saliency Map.