|
GeonU Kim geonukim@kaist.ac.kr I am a Ph.D. student at AMILab in School of Computing at KAIST, supervised by Prof. Dr. Tae-Hyun Oh. |
|
Research Interestes
|
|
|
Reflection-aware Generative Novel View Synthesis
GeonU Kim, Shin Dong-Yeon, Tae-Hyun Oh, ECCV, 2026 project page / arXiv A training-free method for reflection-consistent novel view generation |
|
SplatReasoner: Enhancing Embodied Reasoning and Grounding by Novel View Synthesis
Kim Yu-Ji, Dahye Lee, Kim Jun-Seong, Nam Hyeon-Woo, GeonU Kim, Yongjin Kwon, Yu-Chiang Frank Wang, Jaesung Choe, Tae-Hyun Oh ECCV, 2026 project page / arXiv Novel-view synthesis improves the reasoning capabilities of VLMs in 3D scenes |
|
FPGS: Feed-Forward Semantic-aware Photorealistic Style Transfer of Large-Scale Gaussian Splatting
GeonU Kim, Kim Youwang, Lee Hyoseok, Tae-Hyun Oh, IJCV, 2026 project page / arXiv Feed-forward Gaussian Splatting photorealistic style transfer, with semantic correspondence. |
|
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 project page / arXiv Direct 3D feature embedded Gaussian with product quantization. |
|
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 project page / paper Joint modeling of Hash encoding and multi-resolusion tri-plane for memory efficient neural radiance fields. |
|
|
FPRF: Feed-Forward Photorealistic Style Transfer of Large-Scale 3D Neural Radiance Fields
GeonU Kim, Kim Youwang, Tae-Hyun Oh, AAAI, 2024 project page / arXiv Stylize neural radiance fields with multiple style refernece images, in a feed-forward manner. |
|
Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement
Junuk Cha, Muhammad Saqlain, GeonU Kim, Mingyu Shin, Seungryul Baek, ECCV, 2022 arXiv / code Reconstruct multi-person human meshes from a single image with inverse kinematics and relation-aware refinement. |
|
This website is based on this page. We thank Jon Barron for kindly open-sourcing the source code. |