dengqingkang Goto Github PK

3d-object-reconstruction

This repository consist of python code, input and output images for generating a point cloud obtained from a depth map image of a stereo image pair. Point cloud of an object allows a robot to determine coordinates of every point of that object with respect to world coordinates. It is extremely useful in humanoid robots.

5_laser_camera_sim

batchnormalization

Implementation of batch normalization to avoid overfitting

batchnormalization-1

Batch normalization was introduced in Sergey Ioffe's and Christian Szegedy's 2015 paper Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. The idea is that, instead of just normalizing the inputs to the network, we normalize the inputs to layers within the network. It's called "batch" normalization because during training, we normalize each layer's inputs by using the mean and variance of the values in the current mini-batch.

bilateral_solver

Python code for the fast bilateral solver

conditional-batch-norm

Pytorch implementation of NIPS 2017 paper "Modulating early visual processing by language"

cspn

Convolutional Spatial Propagation Network

cspn_monodepth

Unofficial Faster PyTorch implementation of Convolutional Spatial Propagation Network

deep-photo-styletransfer

Code and data for paper "Deep Photo Style Transfer": https://arxiv.org/abs/1703.07511

deepcompletionrelease

Deep Depth Completion of a Single RGB-D Image

deeplidar

Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Image

depth_map_from_stereo

Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation

dfusenet

ITSC 2019 | This is the accompanying code repository for our paper "DFuseNet: Deep Fusion of RGB and Sparse Depth Information for Image Guided Dense Depth Completion" | PyTorch, Python 3

dsmnet

Pytorch implementation of the several Deep Stereo Matching Network

gc-net-tensorflow

GCNet: End-to-End Learning of Geometry and Context for Deep Stereo Regression (Tensorflow Implementation)

ilcc

Intensity-based_Lidar_Camera_Calibration

kinect_justrecord

(Eyebeam #5 of 13) Records Kinect depth maps as 8-bit grayscale images. Use [ https://github.com/N1ckFG/Kinect_justrecord_post ] to fix sync or [ https://github.com/N1ckFG/Pointcloud_Render ] to batch export OBJ files.

lego-loam

LeGO-LOAM: Lightweight and Ground-Optimized Lidar Odometry and Mapping on Variable Terrain

lidar_imu_calib

浙大开源的Lidar IMU标定工具，适配了自己的数据集。

lidar_imu_calib-1

Targetless Calibration of LiDAR-IMU System Based on Continuous-time Batch Estimation

monodepth-fpn-pytorch

Single Image Depth Estimation with Feature Pyramid Network

pointcloud_render

(Eyebeam #10 of 13) Convert a grayscale depth map image to a point cloud; save in formats including OBJ, PLY, ASC.

revisiting_single_depth_estimation

official implementation of "Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries"

ros_bridge

ROS Bridge Driver for Carla Simulator package : https://github.com/carla-simulator/carla

sdfilter

Code Release for "Static and Dynamic Guidance Filtering" CVPR 2015.

self-supervised-depth-completion

ICRA 2019 "Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera"

sfmlearner

An unsupervised learning framework for depth and ego-motion estimation from monocular videos

slam

transform 2D rgb and depth image to 3D point cloud with color.

solvepnp

opencv solve的算法仓库

stereo-lidar-ccvnorm

Implementation of "Stereo and LiDAR Fusion using Stereo Matching Network with Conditional Cost Volume Normalization"