Chonghyuk (Andrew) Song

I'm a 2nd-year master's student at CMU's Robotics Institute, where I am extremely fortunate to be co-advised by Deva Ramanan and Jun-Yan Zhu. My research interests include 3D reconstruction of in-the-wild dynamic scenes from video, and its application to robotics.

Previously, I was at the Agency for Defense Development (ADD), where I developed autonomous mobile robots as part of my mandatory military service. I graduated from KAIST with a B.S. in Mechanical Engineering.

Email  /  LinkedIn  /  Google Scholar  /  Github

profile photo
Research
Distinctiveness Oriented Positional Equilibrium for Point Cloud Registration
Taewon Min, Chonghyuk Song, Eunseok Kim, Inwook Shim
ICCV, 2021
[paper]

A novel positional embedding module that yields unprecedented improvements in the accuracy of existing GNN-based rigid point cloud registration methods.

Improving Gradient Flow with Unrolled Highway Expectation Maximization
Chonghyuk Song, Eunseok Kim, Inwook Shim
AAAI, 2021
[arXiv]

Replacing unrolled expectation maximization (EM) layers in neural networks with generalized EM layers based on the Newton-Rahpson method introduces highway connections, resulting in improved gradient flow during backpropagation.

Efficient Design Space Exploration of Multi-Mode, Two-Planetary-Gear, Power-Split Hybrid Electric Powertrains via Virtual Levers
Chonghyuk Song, Jaeho Hwang, Dongsuk Kum
IEEE TITS, 2020
[paper]

A highly efficient design methodology that finds the optimal multi-mode, two-planetary-gear powertrain by leveraging the virtual lever, a modeling tool that eliminates the redundancy in the physical design space.


Credits to Jon Barron for this website's template.