Lei He's repositories
tensorflow-vgg
Tensorflow implementation of VGG 16 and VGG 19
AdaptSegNet
Learning to Adapt Structured Output Space for Semantic Segmentation, CVPR 2018 (spotlight)
awesome-semantic-segmentation
awesome-semantic-segmentation
caffe-segnet-cudnn5
This repository was a fork of BVLC/caffe and includes the upsample, bn, dense_image_data and softmax_with_loss (with class weighting) layers of caffe-segnet (https://github.com/alexgkendall/caffe-segnet) to run SegNet with cuDNN version 5.
CASIA-Thesis
自动化所硕博论文模板
cityscapesScripts
README and scripts for the Cityscapes Dataset
coco-json-converter
COCO Json converter python script for DAVIS 2016
dataset-api
Api for visualize sample data, evaluation of different tasks
Deeplab-v2--ResNet-101--Tensorflow
An (re-)implementation of DeepLab v2 (ResNet-101) in TensorFlow for semantic image segmentation on the PASCAL VOC 2012 dataset.
deeplab_v2
基于v2版本的deeplab,使用VGG16模型，在VOC2012，Pascal-context，NYU-v2等多个数据集上进行训练
densenet-tensorflow
DenseNet Implementation in Tensorflow
Detectron
FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.
DSAC
Code for DSAC (Differentiable RANSAC) for Camera Localization, CVPR 17
lanenet-lane-detection
Implemention of lanenet model for real time lane detection using deep neural network model
LapSRN
Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution (CVPR 2017)
leiup.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
Mask_RCNN
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
models
Models and examples built with TensorFlow
monodepth
Unsupervised single image depth prediction with CNNs
MultiNet
Real-time Joint Semantic Reasoning for Autonomous Driving
MultiObjectiveOptimization
Source code for Neural Information Processing Systems (NeurIPS) 2018 paper "Multi-Task Learning as Multi-Objective Optimization"
mvcSnP
Code release for "Multi-view Consistency as Supervisory Signal for Learning Shape and Pose Prediction"
MVSNet
MVSNet: Depth Inference for Unstructured Multi-view Stereo (ECCV2018, Oral Presentaion)
PSPNet
Pyramid Scene Parsing Network
pykitti
Python tools for working with KITTI data.
SfMLearner
An unsupervised learning framework for depth and ego-motion estimation from monocular videos
sparse-to-dense
Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image
subpixel
subpixel: A subpixel convnet for super resolution with Tensorflow