Jisang Han

CV GitHub LinkedIn Scholar

I am a Ph.D student at KAIST AI advised by Seungryong Kim. Currently a Student Researcher at Google DeepMind. Prior to that, I spent a wonderful summer at AI4CE Lab, NYU. I am also closely collaborating with Sony AI, Tokyo.
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.

🎓 Education

KAIST Seoul, Korea

Sep. 2024 - Present

M.S/Ph.D Integrated Student in Artificial Intelligence

Korea University Seoul, Korea

Mar. 2024 - Aug. 2024

Master Student in Computer Science and Engineering

Transferred to KAIST with supervisor

Korea University Seoul, Korea

Mar. 2020 - Feb. 2024

B.S in Computer Science and Engineering

Highest Honor (Ranked 1st in College of Informatics)

🗂️ Experiences

Google Deepmind Zurich, Switzerland

May. 2026 - Nov. 2026, Expected

Student Researcher

Mentor: Thiemo Alldieck

SONY AI Tokyo, Japan

Oct. 2024 - Current

Remote Collaboration

Advisor: Yuki Mitsufuji

New York University (NYU) New York, NY, USA

May. 2025 - Aug. 2025

Visiting Scholar

Advisor: Chen Feng

📖 Publications

Repurposing Geometric Foundation Models for Multi-view Diffusion

Wooseok Jang, Seonghu Jeon, Jisang Han, Jinhyeok Choi, Minkyung Kwon, Seungryong Kim, Saining Xie, Sainan Liu

ECCV 2026 Long Oral ⭐

ArXiv bibtex project page code

@misc{jang2026gld,
    title={Repurposing Geometric Foundation Models for Multi-view Diffusion},
    author={Wooseok Jang and Seonghu Jeon and Jisang Han and Jinhyeok Choi and Minkyung Kwon and Seungryong Kim and Saining Xie and Sainan Liu},
    year={2026},
    eprint={2603.22275},
    archivePrefix={arXiv},
    primaryClass={cs.CV}}

Geometric Action Model for Robot Policy Learning

Jisang Han*, Seonghu Jeon*, Jaewoo Jung, René Zurbrügg, Honggyu An, Tifanny Portela, Marco Hutter, Marc Pollefeys, Seungryong Kim, Sunghwan Hong

ECCVW 2026 workshop on 3D world models

ArXiv bibtex project page code

@misc{han2026gam,
    title={Geometric Action Model for Robot Policy Learning},
    author={Jisang Han and Seonghu Jeon and Jaewoo Jung and Ren\'e Zurbr\"ugg and Honggyu An and Tifanny Portela and Marco Hutter and Marc Pollefeys and Seungryong Kim and Sunghwan Hong},
    year={2026},
    eprint={2606.17046},
    archivePrefix={arXiv},
    primaryClass={cs.CV}}

Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting

Jaewoo Jung*, Jisang Han*, Honggyu An*, Jiwon Kang*, Seonghoon Park*, Seungryong Kim

ECCVW 2026 on Wild3D

ArXiv bibtex project page code

@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}}

Emergent Outlier View Rejection in Visual Geometry Grounded Transformers

Jisang Han*, Sunghwan Hong*, Jaewoo Jung, Wooseok Jang, Honggyu An, Qianqian Wang, Seungryong Kim, Chen Feng

CVPR 2026

ArXiv bibtex project page code

@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}
}

C3G: Learning Compact 3D Representations with 2K Gaussians

Honggyu An*, Jaewoo Jung*, Mungyeong Kim, Sunghwan Hong, Chaehyun Kim, Kazumi Fukuda, Minkyeong Jeon, Jisang Han, Takuya Narihira, Hyuna Ko, Junsu Kim, Yuki Mitsufuji, Seungryong Kim

CVPR 2026

ArXiv bibtex project page code

VIRAL: Visual Representation Alignment for Multimodal Large Language Models

Heeji Yoon*, Jaewoo Jung*, Junwan Kim*, Hyungyu Choi, Heeseong Shin, Sangbeom Lim, Honggyu An, Chaehyun Kim, Jisang Han, Donghyun Kim, Chanho Eom, Sunghwan Hong, Seungryong Kim

ICLR 2026 Workshop on Multimodal Intelligence

ArXiv bibtex project page code

@misc{yoon2025viral,
  title={VIRAL: Visual Representation Alignment for Multimodal Large Language Models},
  author={Heeji Yoon and Jaewoo Jung and Junwan Kim and Hyungyu Choi and Heeseong Shin and Sangbeom Lim and Honggyu An and Chaehyun Kim and Jisang Han and Donghyun Kim and Chanho Eom and Sunghwan Hong and Seungryong Kim},
  year={2025},
  note={arXiv preprint}
}

3D Scene Prompting for Scene-Consistent Camera-Controllable Video Generation

JoungBin Lee*, Jaewoo Jung*, Jisang Han*, Takuya Narihira, Kazumi Fukuda, Junyoung Seo, Sunghwan Hong, Yuki Mitsufuji, Seungryong Kim

ICLR 2026

ArXiv bibtex project page code

Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry

Junyoung Seo*, Jisang Han*, Jaewoo Jung*, Siyoon Jin, JoungBin Lee, Takuya Narihira, Kazumi Fukuda, Takashi Shibuya, Donghoon Ahn, Shoukang Hu, Seungryong Kim, Yuki Mitsufuji

AAAI 2026

ArXiv bibtex project page code

Enhancing 3D Reconstruction for Dynamic Scenes

Jisang Han*, Honggyu An*, Jaewoo Jung*, Takuya Narihira, Junyoung Seo, Kazumi Fukuda, Chaehyun Kim, Sunghwan Hong, Yuki Mitsufuji, Seungryong Kim

NeurIPS 2025

ArXiv bibtex project page code

Self-Evolving Neural Radiance Fields

Jaewoo Jung*, Jisang Han*, Jiwon Kang*, Seongchan Kim, Min-Seop Kwak, Seungryong Kim

ICCV 2025 Workshop on Wild 3D

arXiv bibtex project page code

@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

Sunghwan Hong*, Jaewoo Jung*, Heeseong Shin, Jisang Han, Jioalong Yang, Chong Luo, Seungryong Kim

ICML 2025

ArXiv bibtex project page code

@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

Honggyu An*, Jinhyeon Kim*, Seonghoon Park, Jaewoo Jung, Jisang Han, Sunghwan Hong, Seungryong Kim

CVPR 2025 Highlight ⭐

ArXiv bibtex project page code

@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}, 
}

📗 Preprints

Multi-View Point Tracking as Geometric Supervision for Novel-View Video Generation

JoungBin Lee, Jaewoo Jung, Jongmin Lee, Tongmin Kim, Hyunsung Kim, Takuya Narihira, Kazumi Fukuda, Jahyeok Koo, Jisang Han, Yuki Mitsufuji, Seungryong Kim

ArXiv 2026

ArXiv bibtex project page code

@misc{lee2026mvtrack4gen,
    title={Multi-View Point Tracking as Geometric Supervision for Novel-View Video Generation},
    author={JoungBin Lee and Jaewoo Jung and Jongmin Lee and Tongmin Kim and Hyunsung Kim and Takuya Narihira and Kazumi Fukuda and Jahyeok Koo and Jisang Han and Yuki Mitsufuji and Seungryong Kim},
    year={2026},
    eprint={2606.26087},
    archivePrefix={arXiv},
    primaryClass={cs.CV}}

Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstruction

Mungyeom Kim*, Minkyeong Jeon*, Honggyu An*, Jaewoo Jung, Hyuna Ko, Jisang Han, Hyeonseo Yu, Donghwan Shin, Sunghwan Hong, Takuya Narihira, Kazumi Fukuda, Yuki Mitsufuji, Seungryong Kim

ArXiv 2026

ArXiv bibtex project page code

@misc{kim2026c4g,
    title={Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstruction},
    author={Mungyeom Kim and Minkyeong Jeon and Honggyu An and Jaewoo Jung and Hyuna Ko and Jisang Han and Hyeonseo Yu and Donghwan Shin and Sunghwan Hong and Takuya Narihira and Kazumi Fukuda and Yuki Mitsufuji and Seungryong Kim},
    year={2026},
    eprint={2605.31595},
    archivePrefix={arXiv},
    primaryClass={cs.CV}}