Seoung Wug Oh

Researcher, Adobe Systems

Joined

April 2021

Names

Seoung Wug Oh (Preferred)

Emails

****@adobe.com (Confirmed)

Personal Links

Career & Education History

Researcher

Adobe Systems (adobe.com)

2020 – Present

PhD student

Yonsei University (yonsei.ac.kr)

2014 – 2020

Advisors, Relations & Conflicts

Coauthor

2017 – Present

PhD Advisor

2014 – Present

Expertise

video inpainting

,

video diffusion

,

video editing

,

video generation

,

video synthesis

,

video GAN

2014 – Present

diffusion model

2014 – Present

Publications

VideoMaMa: Mask-Guided Video Matting via Generative Prior
Sangbeom Lim, Seoung Wug Oh, Gabriel, Heeji Yoon, Seungryong Kim, Joon-Young Lee
- CVPR 2026
- Readers: Everyone
IF-MDM: Implicit Face Motion Diffusion Model for Compressing Dynamic Motion Latent
Sejong Yang, Seoung Wug Oh, Yang Zhou, Seon Joo Kim
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
MaGGIe: Masked Guided Gradual Human Instance Matting
Chuong Huynh, Seoung Wug Oh, Abhinav Shrivastava, Joon-Young Lee
- CVPR 2024
- Readers: Everyone
Putting the Object Back into Video Object Segmentation
Ho Kei Cheng, Seoung Wug Oh, Brian L. Price, Joon-Young Lee, Alexander G. Schwing
- CVPR 2024
- Readers: Everyone
THMM-DiT: Talking Head Motion Modeling with Diffusion Transformer
Sejong Yang, Seoung Wug Oh, Yang Zhou, Seon Joo Kim
- 03 Oct 2023 (modified: 25 Sept 2024)
- OpenReview Archive Direct Upload
- Readers: Everyone
Tracking Anything with Decoupled Video Segmentation
Ho Kei Cheng, Seoung Wug Oh, Brian Price, Alexander G. Schwing, Joon-Young Lee
- Published: 01 Jan 2023, Last Modified: 05 Nov 2023
- CoRR 2023
- Readers: Everyone
StylePortraitVideo: Editing Portrait Videos with Expression Optimization
Kwanggyoon Seo, Seoung Wug Oh, Joon-Young Lee, Jingwan Lu, Seonghyeon Kim, Junyong Noh
- 07 Nov 2022
- OpenReview Archive Direct Upload
- Readers: Everyone
Error Compensation Framework for Flow-Guided Video Inpainting
Jaeyeon Kang, Seoung Wug Oh, Seon Joo Kim
- 02 Nov 2022
- OpenReview Archive Direct Upload
- Readers: Everyone
VITA: Video Instance Segmentation via Object Token Association
Miran Heo, Sukjun Hwang, Seoung Wug Oh, Joon-Young Lee, Seon Joo Kim
- Published: 31 Oct 2022, Last Modified: 08 Feb 2026
- NeurIPS 2022 Accept
- Readers: Everyone
Video Instance Segmentation using Inter-Frame Communication Transformers
Sukjun Hwang, Miran Heo, Seoung Wug Oh, Seon Joo Kim
- Published: 09 Nov 2021, Last Modified: 05 May 2023
- NeurIPS 2021 Poster
- Readers: Everyone

View all 11 publications

Co-Authors