2025–26
Physical AI & Probabilistic 4D Reconstruction
- A physics-aware benchmark for dynamic scenes with multi-body interaction
- Probabilistic 4D scene reconstruction from monocular video
- Implicit representation of camera pose
Hello, I'm Mijeong Kim
Ph.D. Candidate · Computer Vision Lab, SNU
My research focuses on 4D world models, probabilistic few-shot dynamic reconstruction, and physical AI, with broad interests in 3D/4D vision and scene understanding. I developed probabilistic representations for reliable 3D/4D reconstruction and modeling of dynamic real-world scenes from limited visual observations.
Research Overview
2024
Uncertainty in Dynamic Scenes & Multi-View Object Tracking
- Uncertainty-aware 4D Gaussian Splatting from monocular video
- Long-term multi-camera multi-object tracking via feature disentanglement
2023
3D Scene Generation
- Mixtures of neural fields for 3D scene generation
- In-the-wild 3D-aware GAN via contrastive learning
2022
Few-Shot 3D Reconstruction & Multi-View Matching
- Few-shot neural volume rendering with InfoNeRF
- Graph convolutional networks for image alignment
News
- Selected as a Rising Star at the Deans’ Forum Women in Engineering Workshop.
- Selected as a Youlchon AI Star.
- Two first-author papers accepted to CVPR 2026.
Experience
Huawei · Noah’s Ark Labs
Sep 2025 – Feb 2026
Applied Scientist Intern · London, UK
Feed-forward 4D reconstruction from monocular video.
Kakao Brain
Jul 2022 – Sep 2022
Research Intern · Seongnam, Korea
3D-aware generation via contrastive learning · ContraNeRF
Selected Publications & Projects
|
PhysGaia: A Physics-Aware Benchmark with Multi-Body Interactions for Dynamic Novel View Synthesis
|
|
GP-4DGS: Probabilistic 4D Gaussian Splatting from Monocular Video via Variational Gaussian Processes
|
|
HyperPose: Hyper-pose Embeddings for 3D-Aware Generative Models with Self-Supervised Disentangling of Pose and Scene
|
|
UA-4DGS: 4D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization
|
|
Generative Neural Fields by Mixtures of Neural Implicit Functions
|
|
ContraNeRF: 3D-Aware Generative Model via Contrastive Learning with Unsupervised Implicit Pose Embedding
|
|
InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering
|
|
Beyond homography: nonparametric image alignment via graph convolutional networks
|
|
Overcoming Forgetting in Federated Learning via Importance From Agent
|
Education
-
Ph.D. in progress · Electrical and Computer Engineering
Computer Vision Lab, Seoul National University, Korea
Advisor: Prof. Bohyung Han
-
B.S. · Naval Architecture and Ocean Engineering
Seoul National University, Korea
Honors & Awards
- Youlchon AI Star – Rising Star PhD (2026)
Selected as a Rising Star PhD in artificial intelligence. - Deans’ Forum Rising Stars Women in Engineering Workshop (2026)
- Kwanjeong Ph.D. Fellowship (2019-2021)
- Science and Engineering Scholarship by President (2014-2018)
- Talent Medal of Korea, Presidential Medal (2014)
Teaching Experience
- Samsung Electronics, Korea (Jul 2019 & Jul 2020)
- Hyundai Motors, Korea (Mar 2020 - Jun 2020)
Digital Computer Concept and Practice Introduction to Python, Dept. of EE in SNU
Research Grants
Deep Learning-Based Pedestrian Removal with Multi-View Data- Fund by Naver (Sep 2019 - Aug 2020)