About Me

I am a Ph.D. candidate in the Dept. of Artificial Intelligence at Korea University, advised by Prof. Sangpil Kim in the Computer Vision Lab. My research focuses on deep learning-based Computer Vision, particularly 3D perception, reconstruction, and scene understanding. I am especially interested in developing visual perception systems that can robustly interpret real-world environments by bridging advances in representation learning, geometry, and practical applications. I have collaborated with Innfarn Yoo and Andreas Lugmayr from Google on generalizable 3D scene reconstruction. More recently, I worked as an Applied Scientist Intern at Amazon Robotics, where I conducted research on RGB-D-based 3D perception for robotic manipulation, with valuable guidance and support from my mentor, Erhan Gundogdu, and my manager, Juxi Leitner.

Seoul, South Korea paulroh@korea.ac.kr
Open to Collaborations

Latest News

Oct 2025
Thrilled to join Amazon Robotics as an Applied Scientist Intern! 🥳
JUN 2025
One paper on 3D Scene Reconstruction is accepted to ICCV 2025.
FEB 2025
One paper on 3D Instance Segmentation is accepted to CVPR 2025.
AUG 2024
Started a research collaboration with Google (Innfan Yoo & Andreas Lugmayr).
MAR 2024
One paper on 3D Instance Segmentation is accepted to CVPR 2024.
DEC 2023
One paper on Domain Adaptation is accepted to AAAI 2024.
OCT 2023
One paper on Recommendation System is accepted to Information Sciences.
AUG 2023
Started a research collaboration with Giljoo Nam from Meta.
AUG 2023
One paper on Action Recognition is accepted to BMVC 2023 (Oral).
OCT 2022
AUG 2022
One paper on 3D Object Detection is accepted to BMVC 2022.
MAR 2022
One paper on Sound-guided Image Manipulation is accepted to CVPR 2022.

Publications

CATSplat
ICCV 2025

CATSplat: Context-Aware Transformer with Spatial Guidance for Generalizable 3D Gaussian Splatting from A Single-View Image

Wonseok Roh, Hwanhee Jung, Jong Wook Kim, Seunggwan Lee, Innfarn Yoo, Andreas Lugmayr, Seunggeun Chi, Karthik Ramani, Sangpil Kim
Insightful Instance Features
CVPR 2025

Insightful Instance Features for 3D Instance Segmentation

Wonseok Roh, Hwanhee Jung, Giljoo Nam, Dong In Lee, Hyeongcheol Park, Sang Ho Yoon, Jungseock Joo, Sangpil Kim
EASE
CVPR 2024

Edge-Aware 3D Instance Segmentation Network with Intelligent Semantic Prior

Wonseok Roh, Hwanhee Jung, Giljoo Nam, Jinseop Yeom, Hyunje Park, Sang Ho Yoon, Sangpil Kim
CMDA
AAAI 2024

CMDA: Cross-Modal and Domain Adversarial Adaptation for LiDAR-Based 3D Object Detection

Gyusam Chang*, Wonseok Roh*, Sujin Jang, Dongwook Lee, Daehyun Ji, Gyeongrok Oh, Jinsun Park, Jinkyu Kim†, Sangpil Kim† (*=Equal contribution)
FHTP
BMVC 2023 Oral

Functional Hand Type Prior for 3D Hand Pose Estimation and Action Recognition from Egocentric View Monocular Videos

Wonseok Roh, Seung Hyun Lee, Won Jeong Ryoo, Jakyung Lee, Gyeongrok Oh, Sooyeon Hwang, Hyung-gun Chi, Sangpil Kim
SMGNN
Information Sciences 2023 IF 8.1

Self-supervised Multimodal Graph Convolutional Network for Collaborative Filtering

Sungjune Kim, Seongjun Yun, Jongwuk Lee, Gyusam Chang, Wonseok Roh, Daneung Sohn, Jungtae Lee, Hogun Park†, Sangpil Kim†
ORA3D
BMVC 2022

ORA3D: Overlap Region Aware Multi-view 3D Object Detection

Wonseok Roh, Gyusam Chang, Seokha Moon, Giljoo Nam, Chanyoung Kim, Younghyun Kim, Sangpil Kim†, Jinkyu Kim†
Sound-guided
CVPR 2022

Sound-guided Semantic Image Manipulation

Seung Hyun Lee, Wonseok Roh, Wonmin Byeon, Sang Ho Yoon, Chanyoung Kim, Jinkyu Kim†, Sangpil Kim†

Patents

SAIT Patent
U.S. Patent

Method and apparatus with object detector training

Sujin Jang, Sangpil Kim, Jinkyu Kim, Wonseok Roh, Gyusam Chang, Dongwook Lee, Daehyun Ji
U.S. Patent Application No. 18/451,287.
Hyundai Patent
U.S. Patent

Apparatus and method for detecting an object and a computer readable recording medium therefor

Younghyun Kim, Seowon Lee, Jinkyu Kim, Sangpil Kim, Wonseok Roh
U.S. Patent Application No. 18/217,904.

Academic Service

Conference Reviewers

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024, 2025, 2026
IEEE/CVF International Conference on Computer Vision (ICCV) 2025
The European Conference on Computer Vision (ECCV) 2026
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023
The Annual Conference on Neural Information Processing Systems (NeurIPS) 2024, 2025
International Conference on Learning Representations (ICLR) 2025