Download PDF

Education

Publications

EgoForce: Robust Online Egocentric Motion Reconstruction via Diffusion Forcing

Inwoo Hwang, Donggeun Lim, Hojun Jang, and Young Min Kim, EgoForce: Robust Online Egocentric Motion Reconstruction via Diffusion Forcing, in Advances in Neural Information Processing Systems (NeurIPS), 2026.

ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation

Inwoo Hwang*, Hojun Jang*, Bing Zhou, Jian Wang, Young Min Kim†, and Chuan Guo†, ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation, in Proceedings of the European Conference on Computer Vision (ECCV), 2026.

* Equal contribution    † Co-corresponding author

Audio-aided Character Control for Inertial Measurement Tracking

Hojun Jang, Jinseok Bae, and Young Min Kim, Audio-aided Character Control for Inertial Measurement Tracking, in European Association for Computer Graphics (Eurographics) short paper, 2025.

ReMP: Reusable Motion Prior for Multi-domain 3D Human Pose Estimation and Motion Inbetweening

Hojun Jang and Young Min Kim, ReMP: Reusable Motion Prior for Multi-domain 3D Human Pose Estimation and Motion Inbetweening, in Proceedings of the Winter Conference on Applications of Computer Vision (WACV), 2025.

Dynamic Mesh Recovery from Partial Point Cloud Sequence

Hojun Jang, Minkwan Kim, Jinseok Bae, and Young Min Kim, Dynamic Mesh Recovery from Partial Point Cloud Sequence, in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023.

LDL: Line Distance Functions for Panoramic Localization

Junho Kim, Changwoon Choi, Hojun Jang, and Young Min Kim, LDL: Line Distance Functions for Panoramic Localization, in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023.

CPO: Change Robust Panorama to Point Cloud Localization

Junho Kim, Hojun Jang, Changwoon Choi, and Young Min Kim, CPO: Change Robust Panorama to Point Cloud Localization, in Proceedings of the European Conference on Computer Vision (ECCV), 2022.

Neural Marionette: Unsupervised Learning of Motion Skeleton and Latent Dynamics from Volumetric Video

Jinseok Bae, Hojun Jang, Cheol-Hui Min, Hyungun Choi, and Young Min Kim, Neural Marionette: Unsupervised Learning of Motion Skeleton and Latent Dynamics from Volumetric Video, in Proceedings of the AAAI Conference on Artificial Intelligence, 2022.

PICCOLO: Point Cloud-Centric Omnidirectional Localization

Junho Kim, Changwoon Choi, Hojun Jang, and Young Min Kim, PICCOLO: Point Cloud-Centric Omnidirectional Localization, in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021.

Patents

• Method, device, and computer-readable medium for colormetry considering external environment (KR10-2596914).
• Method, device, and computer-readable medium for deriving colormetry reference color (KR10-2604699).
• Method and apparatus for estimating camera pose from point clouds using panoramic images (KR10-296785).

Research experience

	LG Electronics, Undergraduate Intern Automatic Korean Spacing using BERT Contextual Language Data Augmentation using BERT	Jul - Aug, 2019
	NAVER LABS Europe, PhD Intern Multi-Person Motion Generation	May - Oct, 2026

Academic Activities

Honors and Awards

Teaching