Welcome to MINDS!

Established in 2020, POSTECH Mathematical Institute for Data Science (MINDS) is the community of researchers in the areas of fundamental data science, machine learning, artificial intelligence, scientific computing, and humanitarian data science. MINDS mission is to provide a platform for collaboration among researchers and to provide various opportunities for students in data science. MINDS also aims to use our data science research to serve our local and global communities pursuing humanitarian data science.

News

🌟 DACON Ranker Special Lecture: Winning Strategies for AI Competitions 🌟 2023.11.30

3nd POSTECH&Peking SIAM Student Chapter Joint Conference 2023.11.01

2023 PSSC Summer Camp 2023.10.04

[POSTECH(포항공과대학교) 수리 데이터과학 연구소 연구계약직 공고]-상시모집 2023.07.25

[POSTECH(포항공과대학교) 수리 데이터과학 연구소 연구계약직 공고] 2023.07.14

[POSTECH(포항공과대학교) 수리 데이터과학 연구소 연구교수 채용 공고] 2023.06.12

Seminar | Joint seminar for probability and mathematical biology 2023.05.02

[POSTECH(포항공과대학교) 수리 데이터과학 연구소 연구계약직 공고] 2023.02.15

Upcoming Events

Schedule

MINDS SEMINAR

MINDS Seminar Series | Myungjoo Kang (Seoul National University) - Deep Learning-Based Surface Reconstruction from Point Clouds

MINDS SEMINAR

period : 2024-11-19 ~ 2024-11-19

time : 17:00:00 ~ 18:00

개최 장소 : Online streaming (Zoom)

Topic : Deep Learning-Based Surface Reconstruction from Point Clouds

개요

Date	2024-11-19 ~ 2024-11-19	Time	17:00:00 ~ 18:00
Speaker	Myungjoo Kang	Affiliation	Seoul National University
Place	Online streaming (Zoom)	Streaming link	ID : 688 896 1076 / PW : 54321
Topic	Deep Learning-Based Surface Reconstruction from Point Clouds
Contents	In this presentation, we introduce an advanced deep learning approach for reconstructing surfaces from unorganized point clouds. By leveraging an implicit surface representation through a level set function, our method ensures watertight results and seamlessly adapts to various topologies. We employ the p-Poisson equation to precisely learn the signed distance function (SDF), improving accuracy through a variable splitting strategy that incorporates the SDF gradient as an auxiliary variable. Additionally, we enforce a curl-free condition on the auxiliary variable to exploit the irrotational nature of conservative vector fields. Our numerical results illustrate that this strategic integration of partial differential equations and key vector field characteristics efficiently reconstructs high-quality surfaces without the need for prior surface knowledge.