Hello, I'm Jaewoo Jung

I am a Ph.D student at KAIST AI advised by Seungryong Kim. I am mainly interested in the problem of 3D/4D Reconstruction & Understanding. Recently, to enable better understanding and reasoning of the real-world, I am also working on enhancing the understandings of VLM models.

CV Scholar Github X Linkedin

News

Publications

Preprints and Domestic Conference

C3G: Learning Compact 3D Representations with 2K Gaussians

NEW !
C3G: Learning Compact 3D Representations with 2K Gaussians

Honggyu An*, Jaewoo Jung*, Mungyeom Kim, Sunghwan Hong, Chaehyun Kim, Kazumi Fukuda, Minkyeong Jeon, Jisang Han, Takuya Narihira, Hyuna Ko, Junsu Kim, Yuki Mitsufuji†, Seungryong Kim†
Arxiv, 2025

Project Page PDF arXiv
Emergent Outlier View Rejection in Visual Geometry Grounded Transformers

NEW !
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†
Arxiv, 2025

Project Page PDF arXiv
3D Scene Prompting for Scene-Consistent Camera-Controllable Video Generation

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†
Arxiv, 2025

Project Page PDF arXiv
VIRAL: Visual Representation Alignment for Multimodal Large Language Models

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
Arxiv, 2025

Project Page PDF arXiv
URECA: Unique Region Caption Anything

URECA: Unique Region Caption Anything

Sangbeom Lim*, Junwan Kim*, Heeji Yoon, Jaewoo Jung, Seungryong Kim†
Arxiv, 2025

Project Page PDF arXiv
Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting

Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting

Jaewoo Jung*, Jisang Han*, Honggyu An*, Jiwon Kang*, Seonghoon Park*, Seungryong Kim†
Arxiv, 2024 350+ Stars

Project Page PDF arXiv

International Conference

Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry

Vid-CamEdit: 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 @ Singapore

Project Page PDF arXiv
D<sup>2</sup>USt3R: Enhancing 3D Reconstruction with 4D Pointmaps for Dynamic Scenes

D2USt3R: Enhancing 3D Reconstruction with 4D Pointmaps 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 @ San Diego

Project Page PDF arXiv
Self-Evolving Neural Radiance Fields

Self-Evolving Neural Radiance Fields

Jaewoo Jung*, Jisang Han*, Jiwon Kang*, Seongchan Kim, Min-Seop Kwak, Seungryong Kim†
ICCVW 2025 @ Honolulu (Workshop on 3D Modeling, Reconstruction, and Generation in the Wild)
IPIU, 2024 @ Jeju Outstanding Paper Award (Silver)

Project Page PDF arXiv
PF3plat : Pose-Free Feed-Forward 3D Gaussian Splatting

PF3plat : Pose-Free Feed-Forward 3D Gaussian Splatting

Sunghwan Hong*, Jaewoo Jung*, Heeseong Shin, Jisang Han, Jiaolong Yang†, Chong Luo†, Seungryong Kim†
ICML, 2025 @ Vancouver

Project Page PDF arXiv
Cross-View Completion Models are Zero-shot Correspondence Estimators

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 @ Nashville Highlight

Project Page PDF arXiv
Domain Generalization using Large Pretrained Models with Mixture-of-Adapters

Domain Generalization using Large Pretrained Models with Mixture-of-Adapters

Gyuseong Lee*, Wooseok Jang*, Jinhyeon Kim, Jaewoo Jung, Seungryong Kim†
WACV, 2025 @ Tucson

Project Page PDF arXiv
Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairs

Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairs

Sunghwan Hong, Jaewoo Jung, Heeseong Shin, Jiaolong Yang†, Seungryong Kim†, Chong Luo†
CVPR, 2024 @ Seattle Highlight

Project Page PDF arXiv

Education

  • KAIST AI, South Korea
    • M.S./Ph.D. Integrated Course in Artificial Intelligence (Advisor : Prof. Seungryong Kim)
    • Sep. 2024 - Present
  • Korea University, South Korea
    • M.S. in Computer Science and Engineering (Advisor : Prof. Seungryong Kim)
    • Mar. 2023 - Aug. 2024 (Incomplete : Transferred to KAIST AI with advisor.)
  • Korea University, South Korea
    • B.S. in Computer Science and Engineering
    • Mar. 2019 - Feb. 2023
    • Graduate with Magna Cum Laude

Academic Services

  • Reviewers
    • ICLR : 2025-26
    • AAAI : 2026
    • WACV : 2025
    • ACM MM : 2024

Honors

  • Outstanding Paper Award (Silver)
    • 36th Workshop on Image Processing and Image Understanding (IPIU2024)

Projects