rennylex Goto Github PK

3d-point-cloud-generation

Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction :grapes: (AAAI 2018)

3d-vision-and-touch

When told to understand the shape of a new object, the most instinctual approach is to pick it up and inspect it with your hand and eyes in tandem. Here, touch provides high fidelity localized information while vision provides complementary global context. However, in 3D shape reconstruction, the complementary fusion of visual and haptic modalities remains largely unexplored. In this paper, we study this problem and present an effective chart-based approach to fusing vision and touch, which leverages advances in graph convolutional networks. To do so, we introduce a dataset of simulated touch and vision signals from the interaction between a robotic hand and a large array of 3D objects. Our results show that (1) leveraging both vision and touch signals consistently improves single-modality baselines, especially when the object is occluded by the hand touching it; (2) our approach outperforms alternative modality fusion methods and strongly benefits from the proposed chart-based structure; (3) reconstruction quality boosts with the number of grasps provided; and (4) the touch information not only enhances the reconstruction at the touch site but also extrapolates to its local neighborhood.

a-stack-based-calculator

This is a basic&simple calculator supporting ➕➖✖➗ and ( ), whose order of priority is achieved by using Stack to store operators and operands. Currently it only features in the calculation of integers. //a double-supporting version is in progress.

active-3d-vision-and-touch

A repository for the paper Active 3D Shape Reconstruction from Vision and Touch and robotic touch simulator package.

adaptive_active_exposure_control

agec

arma-3-script-for-animations-of-take-off-on-air-carriers

This repository includes the scripts i wrote for a Multiplayer Mission in ARMA 3. **** PBOmanager required.

avatarify-python

Avatars for Zoom, Skype and other video-conferencing apps.

blurryfacesup

A tool to blur faces or other regions in images and videos 🤡🔍

cmo-db-requests

Public issue/request tracking for the Command: Modern Operations database

crawl-to-read

A spider exe designed to crawl everything valuable on https://book.douban.com, ranging from the category of History to Novel. Results are sorted according to the rate the books received, and packed up inside a .xlsx file. Pictorial as well as numerical analysis is performed with Matplot, aiming to reflect crucial pieces that are informative for potential readers.

cs-masters-application.github.io

densepcr

Repository for 'Dense 3D Point Cloud Reconstruction Using a Deep Pyramid Network' [WACV 2019]

dffml

The easiest way to use Machine Learning. Mix and match underlying ML libraries and data set sources. Generate new datasets or modify existing ones with ease.

digital-signal-processing-instant-tools

Useful function for DSP in MATLAB. including: classifying voiced /unvoiced sound, acquiring the base frequency for given signal, calculating Short-term zero-crossing rate

exposure_experiment

free-project-course

Free course for Resume, 整理和搜集网络免费的项目实战课程，包括 Java 项目实战，Python 项目实战，C++ 项目实战等

getweather

Use this Web App to get the weather status of your region!

graphics-

gsoc-cn

Google Summer of Code 中文相关资料

impersonator

PyTorch implementation of our ICCV 2019 paper: Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis

leetcode-record

Recording my path of Leetcode.

loveit

❤️A clean, elegant but advanced blog theme for Hugo 一个简洁、优雅且高效的 Hugo 主题

metu

multirobot_system_assign

my-alternate-portfolio-website

Portfolio Website generated using Jekyll, Sass, and Gulp.js, to showcase my web presence, résumé, story, & featured projects with a Particle.js aligned theme.

new-grad-positions-2023

A collection of New Grad full time roles in SWE, Quant, and PM.

node-course-v3-code

Code for version 3 of The Complete Node.js Developer Course

occo

[ICCV' 21] "Unsupervised Point Cloud Pre-training via Occlusion Completion"

ocr_kor_en

:pencil2:Image text detection and Korean, English recognition model implementation in pytorch