AIConfPaper
← Search

Seoung Wug Oh

35 accepted papers

2026

DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation

Tuan Duc Ngo, Jiahui Huang, Seoung Wug Oh, Kevin Blackburn-Matzen, Evangelos Kalogerakis, Chuang Gan +1
CVPR 2026

Estimating accurate, view-consistent geometry and camera poses from uncalibrated multi-view/video inputs remains challenging--especially at high spatial resolutions and over long sequences. We present DAGE, a dual-stream transformer whose main novelty is to disentangle global coherence from fine det

Cited by 0Source ↗code ↗Scholar ↗
2026

VideoMaMa: Mask-Guided Video Matting via Generative Prior

Sangbeom Lim, Seoung Wug Oh, Jiahui Huang, Heeji Yoon, Seungryong Kim, Joon-Young Lee
CVPR 2026

Generalizing video matting models to real-world videos remains a significant challenge due to the scarcity of labeled data. To address this, we present Video Mask-to-Matte Model VideoMaMa that converts coarse segmentation masks into pixel accurate alpha mattes, by leveraging pretrained video diffusi

Cited by 0Source ↗code ↗Scholar ↗
2025

Elevating Flow-Guided Video Inpainting with Reference Generation

Suhwan Cho, Seoung Wug Oh, Sangyoun Lee, Joon-Young Lee
AAAI 2025technical

Video inpainting (VI) is a challenging task that requires effective propagation of observable content across frames while simultaneously generating new content not present in the original video. In this study, we propose a robust and practical VI framework that leverages a large generative model for…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Robust and Consistent Online Video Instance Segmentation via Instance Mask Propagation

Miran Heo, Seoung Wug Oh, Seon Joo Kim, Joon-Young Lee
AAAI 2025technical

Recent advancements in online Video Instance Segmentation (VIS) methods show notable performance improvements across benchmarks. However, the leading methods in the tracking-by-detection paradigm often result in temporally inconsistent predictions at both instance-level and pixel-level that lead to…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

HARIVO: Harnessing Text-to-Image Models for Video Generation

Mingi Kwon, Seoung Wug Oh, Yang Zhou, Joon-Young Lee, Difan Liu, Haoran Cai +3
ECCV 2024poster

"We present a method to create diffusion-based video models from pretrained Text-to-Image (T2I) models. Recently, AnimateDiff proposed freezing the T2I model while only training temporal layers. We advance this method by proposing a unique architecture, incorporating a mapping network and frame-wise…

Cited by 7Source ↗PDF ↗code ↗Scholar ↗
2024

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 2024poster

3D-aware GANs offer new capabilities for view synthesis while preserving the editing functionalities of their 2D counterparts. GAN inversion is a crucial step that seeks the latent code to reconstruct input images or videos subsequently enabling diverse editing tasks through manipulation of this lat…

Cited by 3Source ↗PDF ↗Scholar ↗
2024

MaGGIe: Masked Guided Gradual Human Instance Matting

Chuong Huynh, Seoung Wug Oh, Abhinav Shrivastava, Joon-Young Lee
CVPR 2024poster

Human matting is a foundation task in image and video processing where human foreground pixels are extracted from the input. Prior works either improve the accuracy by additional guidance or improve the temporal consistency of a single instance across frames. We propose a new framework MaGGIe Masked…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗
2024

Putting the Object Back into Video Object Segmentation

Ho Kei Cheng, Seoung Wug Oh, Brian Price, Joon-Young Lee, Alexander Schwing
CVPR 2024highlight

We present Cutie a video object segmentation (VOS) network with object-level memory reading which puts the object representation from memory back into the video object segmentation result. Recent works on VOS employ bottom-up pixel-level memory reading which struggles due to matching noise especiall…

Cited by 98Source ↗PDF ↗code ↗Scholar ↗
2024

VISAGE: Video Instance Segmentation with Appearance-Guided Enhancement

Hanjung Kim, Jaehyun Kang, Miran Heo, Sukjun Hwang, Seoung Wug Oh, Seon Joo Kim*
ECCV 2024poster

"In recent years, online Video Instance Segmentation (VIS) methods have shown remarkable advancement with their powerful query-based detectors. Utilizing the output queries of the detector at the frame-level, these methods achieve high accuracy on challenging benchmarks. However, our observations de…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2023

A Generalized Framework for Video Instance Segmentation

Miran Heo, Sukjun Hwang, Jeongseok Hyun, Hanjung Kim, Seoung Wug Oh, Joon-Young Lee +1
CVPR 2023poster

The handling of long videos with complex and occluded sequences has recently emerged as a new challenge in the video instance segmentation (VIS) community. However, existing methods have limitations in addressing this challenge. We argue that the biggest bottleneck in current approaches is the discr…

Cited by 55Source ↗PDF ↗code ↗Scholar ↗
2023

Tracking Anything with Decoupled Video Segmentation

Ho Kei Cheng, Seoung Wug Oh, Brian Price, Alexander Schwing, Joon-Young Lee
ICCV 2023poster

Training data for video segmentation are expensive to annotate. This impedes extensions of end-to-end algorithms to new video segmentation tasks, especially in large-vocabulary settings. To 'track anything' without training on video data for every individual task, we develop a decoupled video segmen…

Cited by 269PDF ↗code ↗Scholar ↗
2022

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 2022poster

"Scaling object taxonomies is one of the important steps toward a robust real-world deployment of recognition systems. We have faced remarkable progress in images since the introduction of the LVIS benchmark. To continue this success in videos, a new video benchmark, TAO, was recently presented. Giv…

Cited by 8Source ↗PDF ↗Scholar ↗
2022

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 2022poster

Recently, both long-tailed recognition and object tracking have made great advances individually. TAO benchmark presented a mixture of the two, long-tailed object tracking, in order to further reflect the aspect of the real-world. To date, existing solutions have adopted detectors showing robustness…

Cited by 5PDF ↗code ↗Scholar ↗
2022

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 +1
CVPR 2022oral

For online video instance segmentation (VIS), fully utilizing the information from previous frames in an efficient manner is essential for real-time applications. Most previous methods follow a two-stage approach requiring additional computations such as RPN and RoIAlign, and do not fully exploit th…

Cited by 42PDF ↗code ↗Scholar ↗
2022

VITA: Video Instance Segmentation via Object Token Association

Miran Heo, Sukjun Hwang, Seoung Wug Oh, Joon-Young Lee, Seon Joo Kim
NeurIPS 2022accept

We introduce a novel paradigm for offline Video Instance Segmentation (VIS), based on the hypothesis that explicit object-oriented information can be a strong clue for understanding the context of the entire sequence. To this end, we propose VITA, a simple structure built on top of an off-the-shelf…

Cited by 104Source ↗PDF ↗code ↗Scholar ↗
2021

Hierarchical Memory Matching Network for Video Object Segmentation

Hongje Seong, Seoung Wug Oh, Joon-Young Lee, Seongwon Lee, Suhyeon Lee, Euntai Kim
ICCV 2021poster

We present Hierarchical Memory Matching Network (HMMN) for semi-supervised video object segmentation. Based on a recent memory-based method [33], we propose two advanced memory read modules that enable us to perform memory reading in multiple scales while exploiting temporal smoothness. We first pro…

Cited by 149PDF ↗code ↗Scholar ↗
2021

Tackling the Ill-Posedness of Super-Resolution Through Adaptive Target Generation

Younghyun Jo, Seoung Wug Oh, Peter Vajda, Seon Joo Kim
CVPR 2021poster

By the one-to-many nature of the super-resolution (SR) problem, a single low-resolution (LR) image can be mapped to many high-resolution (HR) images. However, learning based SR algorithms are trained to map an LR image to the corresponding ground truth (GT) HR image in the training dataset. The trai…

Cited by 62PDF ↗code ↗Scholar ↗
2021

Video Instance Segmentation using Inter-Frame Communication Transformers

Sukjun Hwang, Miran Heo, Seoung Wug Oh, Seon Joo Kim
NeurIPS 2021poster

We propose a novel end-to-end solution for video instance segmentation (VIS) based on transformers. Recently, the per-clip pipeline shows superior performance over per-frame methods leveraging richer information from multiple frames. However, previous per-clip models require heavy computation and…

Cited by 150Source ↗PDF ↗code ↗Scholar ↗
2020

Cross-Identity Motion Transfer for Arbitrary Objects through Pose-Attentive Video Reassembling

Subin Jeon, Seonghyeon Nam, Seoung Wug Oh, Seon Joo Kim
ECCV 2020poster

We propose an attention-based networks for transferring motions between arbitrary objects. Given a source image(s) and a driving video, our networks animate the subject in the source images according to the motion in the driving video. In our attention mechanism, dense similarities between the learn…

Cited by 13Source ↗PDF ↗Scholar ↗
2020

Deep Space-Time Video Upsampling Networks

Jaeyeon Kang, Younghyun Jo, Seoung Wug Oh, Peter Vajda, Seon Joo Kim
ECCV 2020poster

Video super-resolution (VSR) and frame interpolation (FI) are traditional computer vision problems, and the performance have been improving by incorporating deep learning recently. In this paper, we investigate the problem of jointly upsampling videos both in space and time, which is becoming more i…

Cited by 21Source ↗PDF ↗code ↗Scholar ↗
2019

Fast User-Guided Video Object Segmentation by Interaction-And-Propagation Networks

Seoung Wug Oh, Joon-Young Lee, Ning Xu, Seon Joo Kim
CVPR 2019poster

We present a deep learning method for the interactive video object segmentation. Our method is built upon two core operations, interaction and propagation, and each operation is conducted by Convolutional Neural Networks. The two networks are connected both internally and externally so that the netw…

Cited by 79PDF ↗Scholar ↗
2018

Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation

Younghyun Jo, Seoung Wug Oh, Jaeyeon Kang, Seon Joo Kim
CVPR 2018poster

Video super-resolution (VSR) has become even more important recently to provide high resolution (HR) contents for ultra high definition displays. While many deep learning based VSR methods have been proposed, most of them rely heavily on the accuracy of motion estimation and compensation. We introdu…

Cited by 691Source ↗PDF ↗code ↗Scholar ↗
2018

Fast Video Object Segmentation by Reference-Guided Mask Propagation

Seoung Wug Oh, Joon-Young Lee, Kalyan Sunkavalli, Seon Joo Kim
CVPR 2018poster

We present an efficient method for the semi-supervised video object segmentation. Our method achieves accuracy competitive with state-of-the-art methods while running in a fraction of time compared to others. To this end, we propose a deep Siamese encoder-decoder network that is designed to take adv…

Cited by 512Source ↗PDF ↗Scholar ↗
2016

Do It Yourself Hyperspectral Imaging With Everyday Digital Cameras

Seoung Wug Oh, Michael S. Brown, Marc Pollefeys, Seon Joo Kim
CVPR 2016spotlight

Capturing hyperspectral images requires expensive and specialized hardware that is not readily accessible to most users. Digital cameras, on the other hand, are significantly cheaper in comparison and can be easily purchased and used. In this paper, we present a framework for reconstructing hyperspe…

Cited by 110PDF ↗Scholar ↗