Avatar

Sungwon Hwang

Integrated M.S & Ph.D Candidate

Graduate School of Artificial Intelligence KAIST


CV | Google Scholar


I am an integrated M.S & Ph.D student advised by Professor Jaegul Choo.

My research interests lie in machine learning and computer vision for deep understanding of 3-dimensional scenes, with particular focus on neural volume rendering techniques. Previously published works span point cloud registration algorithm, dynamic object removing algorithm in 3D map consturcted with SLAM, and graph-based rotation invariant representation learning of images.

Contact

  • shwang.14 [at] kaist.ac.kr

  • E3-2, 3240, 291 Daehak-ro, Yuseong-gu, Daejeon, Korea, 34141

Education

  • M.S in Electrical Engineering (Robotics Program), 2022

    KAIST, Korea

    Thesis: "SO(2) Equivariant and Invariant Representation Learning using Graph Convolutional Network"

    Advisor: Prof. Hyun Myung

  • B.S in Mechanical Engineering, 2020

    KAIST, Korea

Publications

  • Equivariance-bridged SO(2)-Invariant Representation Learning using Graph Convolutional Network

    Sungwon Hwang, Hyungtae Lim, Hyun Myung

    BMVC 2021 (Acceptance rate: 437/1206 ≈ 36%)

    [ Paper / Code ]

  • ERASOR: Egocentric Ratio of Psuedo Occupancy-based Dynamic Object Removal for Static 3D Point Cloud Map Building

    Hyungtae Lim, Sungwon Hwang, Hyun Myung

    IEEE RA-Letters (ICRA '21 Option)

    [ Paper / Code ]

  • Normal Distributions Transform is Enough: Real-time 3D Scan Matching for Pose Correction of Mobile Robot

    under Large Odometry Uncertainties

    Hyungtae Lim*, Sungwon Hwang*, Sungjae Shin, Hyun Myung (* equal contribution)

    ICCAS 2020

    [ Paper / Video ]

Awards

  • Student Best Paper Award, ICCAS '20

Academic Activities

Reviewer

  • IEEE Robotics and Automation Letters (ICRA '21 option)