Sunghun Yang

I am an integrated M.S/Ph.D student of computer vision at Yonsei University. I am interested in exploring Computer Vision.

To know more about me, please check the information below.

profile photo
News
Jan 21, 2026
Presented at AAAI 2026, Singapore. (Acceptance rate: 17.6%)
  • [AAAI 2026] MonoCLUE: Object-Aware Clustering Enhances Monocular 3D Object Detection
Oct 19, 2025
Presented at ICCVW 2025, Honolulu, Hawaii, USA.
  • [ICCVW 2025] TransFlow: Motion Knowledge Transfer from Video Diffusion Models to Video Salient Object Detection
Jun 11, 2025
Presented at CVPR 2025, Nashville, Tennessee, USA. (Acceptance rate: 3.3%)
  • [CVPR 2025] Effective SAM Combination for Open-Vocabulary Semantic Segmentation – Oral presentation!
Feb 25, 2025
Presented at AAAI 2025, Philadelphia, Pennsylvania, USA. (Acceptance rate: 23.4%)
  • [AAAI 2025] Video Diffusion Models are Strong Video Inpainter
Publications
Title MonoCLUE : Object-Aware Clustering Enhances Monocular 3D Object Detection
Authors Sunghun Yang, Minhyeok Lee, Jungho Lee, Sangyoun Lee
Venue The Association for the Advancement of Artificial Intelligence (AAAI), 2026
arXiv code
Title SwiftVGGT: A Scalable Visual Geometry Grounded Transformer for Large-Scale Scenes
Authors Jungho Lee, Minhyeok Lee, Sunghun Yang, Minseok Kang, Sangyoun Lee
Venue arXiv, 2026
project page arXiv code
Title TransFlow: Motion Knowledge Transfer from Video Diffusion Models to Video Salient Object Detection + more
Authors Suhwan Cho, Minhyeok Lee, Jungho Lee, Sunghun Yang, Sangyoun Lee
Venue IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), 2025
arXiv code
Title Effective SAM Combination for Open-Vocabulary Semantic Segmentation
Authors Minhyeok Lee, Suhwan Cho, Jungho Lee, Sunghun Yang , Heeseung Choi, Ig-Jae Kim, Sangyoun Lee + more
Venue IEEE/CVF Computer Vision and Pattern Recognition (CVPR), 2025
arXiv
Title Video Diffusion Models are Strong Video Inpainter
Authors Minhyeok Lee, Suhwan Cho, Chajin Shin, Jungho Lee, Sunghun Yang , Sangyoun Lee + more
Venue The Association for the Advancement of Artificial Intelligence (AAAI), 2025
arXiv code
Title STATIC: Surface Temporal Affine for TIme Consistency in Video Monocular Depth Estimation + more
Authors Sunghun Yang, Minhyeok Lee, Suhwan Cho Jungho Lee, Sangyoun Lee
Venue arXiv, 2025
arXiv code
Resume

You can view or download my full CV below.

This website's source code is borrowed from Jon Barron's website template.

Last updated 2026.