Seoung Wug Oh

I’m a Research Scientist at Adobe Research. Previously, I completed my Ph.D. at Yonsei University under the supervision of Prof. Seon Joo Kim. My research focuses on video perception, understanding, and representation. I’m always open to collaborating with strong graduate students, please feel free to reach out if you’re interested.

Research Highlights

• Object Mask Tool in Premiere Pro, 2025

• Roto Brush 3 in After Effects, 2023

• Remove Background Video in Adobe Express, 2023

• Roto Brush 2 in After Effects, 2020

Publications

2025

Tuning-Free Multi-Event Long Video Generation via Synchronized Coupled Sampling

Subin Kim, Seoung Wug Oh, Jui-Hsien Wang, Joon-Young Lee, Jinwoo Shin

ICCV 2025 Workshop - Findings
[paper] [project]

EntitySAM: Segment Everything in Video
Mingqiao Ye, Seoung Wug Oh, Lei Ke, Joon-Young Lee
CVPR 2025
[paper] [project]

Robust and Consistent Online Video Instance Segmentation via Instance Mask Propagation

Miran Heo, Seoung Wug Oh, Seon Joo Kim, Joon-Young Lee
AAAI 2025
[paper] 

Elevating Flow-Guided Video Inpainting with Reference Generation
Suhwan Cho, Seoung Wug Oh, Sangyoun Lee, Joon-Young Lee
AAAI 2025
[paper] [project]

2024

Harnessing Text-to-Image Models for Video Generation
Mingi Kwon, Seoung Wug Oh, Yang Zhou, Difan Liu, Joon-Young Lee, Haoran Cai, Baqiao Liu, Feng Liu, Youngjung Uh
ECCV 2024
[paper] [project]

VISAGE: Video Instance Segmentation with Appearance-Guided Enhancement
Hanjung Kim, Jaehyun Kang, Miran Heo, Sukjun Hwang, Seoung Wug Oh, Seon Joo Kim
ECCV 2024
[paper] [project] [code] 

Putting the Object Back into Video Object Segmentation
Ho Kei Cheng, Seoung Wug Oh, Brian Price, Joon-Young Lee, Alexander Schwing
CVPR 2024 - Highlight
[paper] [project] [code]

MaGGIe: Masked Guided Gradual Human Instance Matting
Chuong Minh Huynh, Seoung Wug Oh, Abhinav Shrivastava, Joon-Young Lee
CVPR 2024
[paper] [project] [code]

In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing
Yiran Xu, Zhixin Shu, Cameron Smith, Seoung Wug Oh, Jia-Bin Huang
CVPR 2024
[paper] [project] [code]

2023

DEVA: Tracking Anything with Decoupled Video Segmentation
Ho Kei Cheng, Seoung Wug Oh, Brian Price, Alexander Schwing, Joon-Young Lee
ICCV 2023
[paper] [project] [code]

A Generalized Framework for Video Instance Segmentation
Miran Heo, Sukjun Hwang, Jeongseok HYUN, Hanjung Kim, Seoung Wug Oh, Joon-Young Lee, Seon Joo Kim
CVPR 2023
[paper] [code]

Mask-guided Matting in the Wild
Kwanyong Park, Sanghyun Woo, Seoung Wug Oh, In So Kweon, Joon-Young Lee
CVPR 2023
[paper]

2022

VITA: Video Instance Segmentation via Object Token Association
Miran Heo*, Sukjun Hwang*, Seoung Wug Oh, Joon-Young Lee, Seon Joo Kim
NeurIPS 2022
[paper] [code]

StylePortraitVideo: Editing Portrait Videos with Expression Optimization
Kwanggyoon Seo, Seoung Wug Oh, Jingwan Lu, Joon-Young Lee, Seonghyeon Kim, Junyon Noh
Pacific Graphics, 2022
[paper] [page]

Error Compensation Framework for Flow-Guided Video Inpainting
Jaeyeon Kang, Seoung Wug Oh, Seon Joo Kim
ECCV 2022
[paper] [code]

Tracking by Associating Clips
Sanghyun Woo, Kwanyong Park, Seoung Wug Oh, In So Kweon, Joon-Young Lee
ECCV 2022
[paper]

Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detection
Sanghyun Woo, Kwanyong Park, Seoung Wug Oh, In So Kweon, Joon-Young Lee
ECCV 2022
[paper] [supp]

One-Trimap Video Matting
Hongje Seong, Seoung Wug Oh, Brian Price, Euntai Kim, Joon-Young Lee
ECCV 2022
[paper] [supp] [code]

Integrating Pose and Mask Predictions for Multi-person in Videos
Miran Heo, Sukjun Hwang, Seoung Wug Oh, Joon-Young Lee, Seon Joo Kim
CVPRW-ECV, 2022
[paper]

VISOLO: Grid-Based Space-Time Aggregation for Efficient Online Video Instance Segmentation
Su Ho Han, Sukjun Hwang, Seoung Wug Oh, Yeonchool Park, Hyunwoo Kim, Min-Jung Kim, Seon Joo Kim
CVPR 2022 - Oral
[paper] [code]

Per-Clip Video Object Segmentation
Kwanyong Park, Sanghyun Woo, Seoung Wug Oh, In So Kweon, Joon-Young Lee
CVPR 2022
[paper] [video] [code]

Cannot See the Forest for the Trees: Aggregating Multiple Viewpoints to Better Classify Objects in Videos
Sukjun Hwang, Miran Heo, Seoung Wug Oh, Seon Joo Kim
CVPR 2022
[paper] [code]

Single-Shot Path Integrated Panoptic Segmentation
Sukjun Hwang, Seoung Wug Oh, Seon Joo Kim
WACV 2022
[paper]

2021

Video Instance Segmentation using Inter-Frame Communication Transformers
Sukjun Hwang, Miran Heo, Seoung Wug Oh, Seon Joo Kim
NeurIPS 2021
[paper] [code]

Hierarchical Memory Matching Network for Video Object Segmentation
Hongje Seong, Seoung Wug Oh, Joon-Young Lee, Seongwon Lee, Suhyeon Lee, Euntai Kim
ICCV 2021
[paper]  [code] [video]

Tackling the Ill-Posedness of Super-Resolution Through Adaptive Target Generation
Younghyun Jo, Seoung Wug Oh, Peter Vajda, Seon Joo Kim
CVPR 2021
[paper] [supp]

Polygonal Point Set Tracking
Gunhee Nam, Miran Heo, Seoung Wug Oh, Joon-Young Lee, Seon Joo Kim
CVPR 2021
[paper] [supp]

Exemplar-Based Open-Set Panoptic Segmentation Network
Jaedong Hwang, Seoung Wug Oh, Joon-Young Lee, Bohyung Han
CVPR 2021
[paper] [supp]

2020

Space-time Memory Networks for Video Object Segmentation with User Guidance
Seoung Wug Oh, Joon-Young Lee, Ning Xu, Seon Joo Kim
TPAMI 2020
[paper] [code] [video] [demo] 

Deep Space-Time Video Upsampling Networks
Jaeyeon Kang, Younghyun Jo, Seoung Wug Oh, Peter Vajda, Seon Joo Kim
ECCV 2020
[arxiv] [video] [code]

Cross-Identity Motion Transfer for Arbitrary Objects through Pose-Attentive Video Reassembling
Subin Jeon, Seonghyeon Nam, Seoung Wug Oh, Seon Joo Kim
ECCV 2020
[paper]

DMV: Visual Object Tracking via Part-level Dense Memory and Voting-based Retrieval
Gunhee Nam, Seoung Wug Oh, Joon-Young Lee,  Seon Joo Kim
[arxiv]

Learning the Loss Functions in a Discriminative Space for Video Restoration
Younghyun Jo, Jaeyeon Kang, Seoung Wug Oh, Seonghyeon Nam, Peter Vajda, Seon Joo Kim
[arxiv]

2019

Onion-Peel Networks for Deep Video Completion
Seoung Wug Oh, Sungho Lee, Joon-Young Lee,  Seon Joo Kim
ICCV 2019
[paper] [supp] [video] [code] 

Copy-and-Paste Networks for Deep Video Inpainting
Sungho Lee, Seoung Wug Oh, DaeYeun Won,  Seon Joo Kim
ICCV 2019
[paper] [video] [code] 

Video Object Segmentation using Space-Time Memory Networks
Seoung Wug Oh, Joon-Young Lee, Ning Xu, Seon Joo Kim
ICCV 2019 - Oral (4.3%)
[paper] [supp] [video] [code] 

• Algorithm behind RotoBrush 2 in Adobe After Effects

Fast User-Guided Video Object Segmentation by Interaction-and-Propagation Networks
Seoung Wug Oh, Joon-Young Lee, Ning Xu, Seon Joo Kim
CVPR 2019
[paper] [demo video] [code]

2016-2018

Fast Video Object Segmentation by Reference-Guided Mask Propagation
Seoung Wug Oh, Joon-Young Lee, Kalyan Sunkavalli, Seon Joo Kim
CVPR 2018   [Spotlight presentation]
[paper] [code]

Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation
Younghyun Jo, Seoung Wug Oh, Jaeyeon Kang, Seon Joo Kim
CVPR 2018
[paper] [code]

Do It Yourself Hyperspectral Imaging with Everyday Digital Cameras
Seoung Wug Oh, Michael S. Brown, Marc Pollefeys, Seon Joo Kim
CVPR 2016 - Spotlight (9.7%)
[paper]

Approaching the Computational Color Constancy as a Classification Problem through Deep Learning
Seoung Wug Oh, Seon Joo Kim
Pattern Recognition, Volume 61, January 2017, Pages 405-416.
[paper] [pdf] 

Awards

• • Silver prize in Samsung Humantech Paper Award, 2019

  • Excellent Research Scholarship, 2016, (Dept. of Computer Science, Yonsei University)

  • NAVER Ph.D.Fellowship Award, 2016, (NAVER Corporation)