Kim Junseong

Kim Junseong

I am a joint MS-Ph.D. student at AMILab in Electrical Engineering at POSTECH, advised by Tae-Hyun Oh. Previously, I completed my B.S. in Electrical Engineering at POSTECH.

I work on research projects at the intersection of computer graphics, vision, and machine learning. My research lies in 3D machine perception including, 3D Reconstruction, Neural rendering, and Computational Photography, but not limited to.

junseong.kim@postech.ac.kr | CV | Google Scholar | GitHub

News

06/2026 Two papers SA-ResGS and SplatReasoner accepted at ECCV 2026.
06/2026 Our paper about real-time motion magnification is accepted at TMLR 2026.
01/2026 Our paper HDR-NSFF is accepted at ICLR 2026.
11/2025 Winner of Qualcomm Innovation Fellowship Korea ($4,000), 2025
05/2025 I am selected as an outstanding reviewer (top 5.64%) at CVPR 2025.
02/2025 Our paper Dr.Splat is accepted for Highlight at CVPR 2025 (highlight Top 3.7%).
---- show more ----

Research Experiences

Huawei Noah’s Ark Lab 3D Imaging Team, London.Jan 2025 - July 2025
   Research Intern, working with Eduardo Pérez Pellitero.
, and Young Kyoon Jang.
NVIDIA Research Taiwan, Taiwan.Feb 2024 - Dec 2025
   Academic Collaboration, working with jaesung-choe.
Naver AI lab - 3D NeRF team, South Korea.Feb 2023 - Aug 2023
   Research Intern, worked with Jin-Hwa Kim.
POSTECH - Algorithmic Machine Intelligence lab, Pohang, Korea.Sep 2021 - Present
   Graduate Student, working with Tae-Hyun Oh.

Publications

SA-ResGS: Self-Augmented Residual 3D Gaussian Splatting for Next Best View Selection
Kim Jun-Seong, Tae-Hyun Oh, Eduardo Pérez-Pellitero, Youngkyoon Jang
ECCV, 2026
Paper |

SplatReasoner: Enhancing Embodied Reasoning and Grounding by Novel View Synthesis
Kim Yu-Ji, Dahye Lee, Kim Jun-Seong, GeonU Kim, Nam Hyeon-Woo, Yongjin Kwon, Yu-Chiang Frank Wang, Jaesung Choe, Tae-Hyun Oh
ECCV, 2026
Project page | Paper |

Revisiting Learning-based Video Motion Magnification for Real time processing
Hyunwoo Ha, Oh Hyun-Bin, Kim Jun-Seong, Kwon Byung-Ki, Kim Sung-Bin, Linh-Tam Tran, Ji-Yun Kim, Sung-Ho Bae, Tae-Hyun Oh
TMLR 2026
Paper

HDR-NSFF: High Dynamic Range Neural Scene Flow Fields
Shin Dong-Yeon, Kim Jun-Seong, Kwon Byung-Ki, Tae-Hyun Oh
ICLR, 2026
Project page | Paper |

Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration
Kim Jun-Seong, GeonU Kim, Kim Yu-Ji, Yu-Chiang Frank Wang, Jaesung Choe†, Tae-Hyun Oh†
CVPR, 2025 (highlight Top 3.7%)
(Winner of Qualcomm Innovation Fellowship Korea)
Project page | Paper |

SoundBrush: Sound as a Brush for Visual Scene Editing
Kim Sung-Bin, Kim Jun-Seong, Junseok Ko, Yewon Kim, Tae-Hyun Oh
AAAI, 2025
Project page | Paper |

Factorized Multi-Resolution HashGrid for Efficient Neural Radiance Fields: Execution on Edge-Devices
Kim Jun-Seong*, Mingyu Kim*, GeonU Kim, Tae-Hyun Oh, Jin-Hwa Kim
RA-L, 2024
- Presented in ICRA, 2025, Atlanta
Project page | Paper |

Learning-based Axial Motion Magnification
Kwon Byung-Ki, Oh Hyun-Bin, Kim Jun-Seong, Hyunwoo Ha, Tae-Hyun Oh
ECCV 2024
Project page | Paper |

Synergistic Integration of Coordinate Network and Tensorial Feature for Improving Neural Radiance Fields from Sparse Inputs
Mingyu Kim, Kim Jun-Seong, Se-Young Yun, Jin-Hwa Kim
ICML 2024
Project page | Paper

HDR-Plenoxels: Self-Calibrating High Dynamic Range Radiance Fields
Kim Jun-Seong*, Kim Yu-Ji*, Moon Ye-Bin, Tae-Hyun Oh
ECCV 2022
Project page | Paper | Video
- Presented in Learning 3D with Multi-View Supervision Workshop (3DMV) at CVPR 2023

Awards and Honors

Academic Services