I am a Ph.D student at KAIST AI advised by Seungryong Kim. My research interests lie in the intersection of computer vision and machine learning, particularly in 3D computer vision and generative models. My goal is to solve fundamental problems in 3D computer vision and apply them to real-world scenarios.
π Education
KAIST Seoul, Korea
Sep. 2024 - PresentM.S/Ph.D Integrated Student in Artificial Intelligence
Korea University Seoul, Korea
Mar. 2024 - Aug. 2024Master Student in Computer Science and Engineering
Transferred to KAIST with supervisor
Korea University Seoul, Korea
Mar. 2020 - Feb. 2024B.S in Computer Science and Engineering
Highest Honor (Ranked 1st in College of Informatics)
ποΈ Experiences

Google Deepmind Zurich, Switzerland
May. 2026 - Nov. 2026, ExpectedStudent Researcher
Mentor: Thiemo Alldieck

SONY AI Tokyo, Japan
Oct. 2024 - CurrentRemote Collaboration
Advisor: Yuki Mitsufuji

π Publications

3D Scene Prompting for Scene-Consistent Camera-Controllable Video Generation
ICLR 2026
Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry
AAAI 2026


Self-Evolving Neural Radiance Fields
ICCV 2025 Workshop on Wild 3D
@article{jung2023self,
title={Self-Evolving Neural Radiance Fields},
author={Jung, Jaewoo and Han, Jisang and Kang, Jiwon and Kim, Seongchan and Kwak, Min-Seop and Kim, Seungryong},
journal={arXiv preprint arXiv:2312.01003},
year={2023}}PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting
ICML 2025
@misc{hong2024pf3plat,
title={PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting},
author={Sunghwan Hong and Jaewoo Jung and Heeseong Shin and Jisang Han and Jiaolong Yang and Chong Luo and Seungryong Kim},
year={2024},
eprint={2410.22128},
archivePrefix={arXiv},
primaryClass={cs.CV}}
Cross-View Completion Models are Zero-shot Correspondence Estimators
CVPR 2025 Highlight β
@misc{an2024crossviewcompletionmodelszeroshot,
title={Cross-View Completion Models are Zero-shot Correspondence Estimators},
author={Honggyu An and Jinhyeon Kim and Seonghoon Park and Jaewoo Jung and Jisang Han and Sunghwan Hong and Seungryong Kim},
year={2024},
eprint={2412.09072},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2412.09072},
}π Preprints

Emergent Outlier View Rejection in Visual Geometry Grounded Transformers
ArXiv 2025
@article{han2025emergent,
title={Emergent Outlier View Rejection in Visual Geometry Grounded Transformers},
author={Han, Jisang and Hong, Sunghwan and Jung, Jaewoo and Jang, Wooseok and An, Honggyu and Wang, Qianqian and Kim, Seungryong and Feng, Chen},
journal={arXiv preprint arXiv:2512.04012},
year={2025}
}
VIRAL: Visual Representation Alignment for Multimodal Large Language Models
ArXiv 2025

Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting
ArXiv 2024
@misc{jung2024relaxing,
title={Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting},
author={Jaewoo Jung and Jisang Han and Honggyu An and Jiwon Kang and Seonghoon Park and Seungryong Kim},
year={2024},
eprint={2403.09413},
archivePrefix={arXiv},
primaryClass={cs.CV}}