Last updated: Apr. 2024

Jaeyoung Chung

I am a Ph.D student in Computer Vision Lab at Seoul National University, advised by Kyoung Mu Lee. For my undergraduate studies, I majored in Electrical and Computer Engineering at the same university.

In the winter of 2021, I was an intern in Intelligent Multimedia Group in Microsoft Research Asia. I have served as a reviewer for CVPR, ECCV, AAAI, and TPAMI.

Email  /  Google Scholar  /  GitHub

⬇️ Hover for videos!


Research
ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian Splattings
Suyoung Lee*, Jaeyoung Chung*, Jaeyoo Huh, Kyoung Mu Lee,
Conference and Workshop on Neural Information Processing Systems (NeurIPS) 2024
project page / arXiv / paper / code

We introduce a method to optimize Gaussian splatting with 360 panorama images, considering omnidirectional camera model.

LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes
Jaeyoung Chung*, Suyoung Lee*, Hyeongjin Nam, Jaerin Lee, Kyoung Mu Lee,
project page / arXiv / code

We developed a 3D Gaussian splatting scene generation pipeline that iteratively generates and aligns parts of the scene.

Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Images
Jaeyoung Chung, Jeongtaek Oh, Kyoung Mu Lee,
Conference on Computer Vision and Pattern Recognition Workshop (CVPRW) 2024
project page / arXiv / code

We introduce a method to optimize Gaussian splatting with a limited image set, mitigating overfitting by incorporating a estimated depth map as a geometric guide.

MEIL-NeRF: Memory-Efficient Incremental Learning of Neural Radiance Fields
Jaeyoung Chung, Kanggeon Lee, Sungyong Baik, Kyoung Mu Lee,
project page / arXiv / code

We study the incremental learning scenario in Neural Radiance Fields (NeRF) first time and propose a self-distillation-based method alleviating catastrophic forgetting without memory increasing.

3DIAS: 3D Shape Reconstruction with Implicit Algebraic Surfaces
Mohsen Yavartanoo*, Jaeyoung Chung*, Reyhaneh Neshatavar, Kyoung Mu Lee,
International Conference on Computer Vision (ICCV), 2021
project page / arXiv / video / code

We propose a constrained implicit algebraic surface as the primitive with few learnable coefficients and higher geometrical complexities.

Monocular Visual-Inertial-Wheel Odometry Using Low-Grade IMU in Urban Areas
Jae Hyung Jung, Jaehyuck Cha, Jae Young Chung, Tae Ihn Kim, Myung Hwan Seo, Sang Yeon Park, Jong Yun Yeo, Chan Gook Park,
IEEE Transactions on Intelligent Transportation Systems, 2020

Effect of Wheel Odometer on Low-Cost Visual-Inertial Navigation System for Ground Vehicles
Jaehyuck Cha, Jae Hyung Jung, Jaeyoung Chung, Tae Ihn Kim, Myung Hwan Seo, Sang Yeon Park, Jong Yun Yeo, Chan Gook Park,
IEEE/ION Position, Location and Navigation Symposium (PLANS), 2020

Rapid Initialization using Relative Pose Constraints in Stereo Visual-Inertial Odometry
Jae Hyung Jung, Jaeyoung Chung, Jaehyuck Cha, Chan Gook Park,
IEEE 15th International Conference on Control and Automation (ICCA), 2019

We propose a precise navigation system using wheel odometry, Low-Grade inertial measurement unit, and monocular camera in Urban Area. VIO Simluation code (Pended)


Team Project
Sounding Rocket Development
Jaeyoung Chung, Daehwan Kim, Beom Park, Soobeom Heo, Deokhyun Kim, and other Hanaro Team members
Gold prize in Contest held by The National Universities' Rocket Association (NURA), summer 2017
Hanaro homepage / promotion video / 2016 NURA video / 2017 NURA video /
code (rocket pin control) / data(recorded INS data during rocket flight)

We develop whole solid sounding rockets from engine, fuel, body, electric system including wing control, parachute control, ignition control, data(pressure, accel, rotation) measurement, and communication system.

I was a leader of electric system team. (2016 ~ 2017)

Alpha-D: Developing drone controlled by reinforcement learning
Yongjae Kim, Jaeyoung Chung, Joonyoung Jang, Chanyoung Jung
Spring ~ fall 2016
code (ROS) / code (GPS/INS, Kalman Filter)

We develop the whole system of quadcopter drone from scratch and try to control some complex movement by utilizing reinforcement learning.

SNU E-Wheel
Taehyung Kim, Jaeyoung Chung, Jigang Kim, Hyerin Choi, Kevin Nam
First prize in Dongbu Award for SNU Creative Design Fair, summer and fall 2015
poster / video

We develop an electronic bicycle with an interchangeable front wheel between motor-powered wheel and normal. We design the motor control system deliberately for similar user experiences with pedal assistance system (PAS).

I mainly develop embedded system and algorithm including power, circuit, PID control, etc.

X-mas Tree for Nerds
Jaeyoung Chung
Chrismas season, 2015

I made this tree out of discarded materials including green pcb-boards (as leaf), shiny light LED arrays, a drone that reacts when approached, and a blower that floats a ping-pong ball


Award
trophy

Best Paper Runner-up Awards at the CVPR 2024 Workshop for Learning 3D with Multi-View Supervision (2024)

“Stars of Tomorrow” Award in Microsoft Research Asia Internship (2022)

Gold Prize at 33th Workshop on Image Processing and Image Understanding (2021)

First Prize at Dongbu Award for SNU Creative Design Fair (2015)


Mini Project (Click)
missing

Handmade RCcar

missing

LogicDesigned TankGame

missing

Pulsejet-powered Cart

missing

Finger-controlled Carnival Board


Teaching (Click)
teaching


Taught high school students embedded system at Doseon high school (Oct. - Nov. 2020)

Taught freshman embedded system design (Mar. - Jun. 2016)

Taught high school students Arduino at Gwangyang Jecheol high school (Jan. - Feb. 2015)


Hobby (Click)
missing
missing
missing
missing


I borrow this format from Ben Mildenhall website.