About Me
Seonghu Jeon
M.S. Student @ KAIST CVLAB
I study 3D/4D vision and generative models, exploring how AI can understand and reconstruct dynamic 3D environments and interact with them through robotics.
News
2026.03Joined KAIST CVLAB as an M.S. student!
2026.02CAMEO accepted to CVPR 2026
2025.07ReMoTE accepted to ITC-CSCC as Oral presentation
Experience
M.S. Student
KAIST CVLAB · 2026 -
Research Intern
KAIST CVLAB · 2023 - 2026
B.S. in Computer Science & Engineering
Korea University (4.46/4.50) · 2022 - 2026 · Graduated with Great Honors
Research Interests
Selected Publications
Repurposing Geometric Foundation Models for Multi-view Diffusion
Paper
Project
Code
CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion Models
Paper
Project
Code
Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching
Paper
Project
Code
ReMoTE: A Benchmark for Object Motion Transfer
Paper