Dong-Hwi Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Dong-Hwi Kim has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Sang-Hyo Park
Kyungpook National University
5 shared publications - Chaewon Moon
Kyungpook National University, Daegu, Republic of Korea
3 shared publications - Dabin Kang
School of Computer Science and Engineering, Kyungpook National University, Daegu, South Korea
2 shared publications - Eunji Kim2 shared publications
- Jehee Kim
Kyungpook National University, Daegu, Republic of Korea
2 shared publications Aro Kim
School of Computer Science and Engineering Kyungpook National University Daegu South Korea
1 shared publication
Latest Publications
- Open Access
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
CompMVR: Compression-Aware Multi-View Restoration Using Diffusion Models for Geometrically Consistent 3D Reconstruction
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessCompMVR: Compression-Aware Multi-View Restoration Using Diffusion Models for Geometrically Consistent 3D Reconstruction
- Open Access
- 31 January 2026
- Published by The Korean Institute of Broadcast and Media Engineers in Journal of Broadcast Engineering
- Vol. 31 (1) , 2-15
Performance Analysis of VGGT with Denoising under Various Compression Levels in Lossy Compression
- 31 January 2026
- Published by The Korean Institute of Broadcast and Media Engineers in Journal of Broadcast Engineering
- Vol. 31 (1) , 2-15
Open AccessPerformance Analysis of VGGT with Denoising under Various Compression Levels in Lossy Compression
- Open Access
- 31 January 2025
- Published by The Korean Institute of Broadcast and Media Engineers in Journal of Broadcast Engineering
- Vol. 30 (1) , 61-71
User-based Mask Generation Method using Object Tracking for Video Inpainting
- 31 January 2025
- Published by The Korean Institute of Broadcast and Media Engineers in Journal of Broadcast Engineering
- Vol. 30 (1) , 61-71
Open AccessUser-based Mask Generation Method using Object Tracking for Video Inpainting
- Open Access
- 31 December 2024
- Published by The Korean Institute of Broadcast and Media Engineers in Journal of Broadcast Engineering
- Vol. 29 (7) , 1136-1146
A Study on the Vulnerability of Semantic Segmentation Model to Data Transformation
- 31 December 2024
- Published by The Korean Institute of Broadcast and Media Engineers in Journal of Broadcast Engineering
- Vol. 29 (7) , 1136-1146
Open AccessA Study on the Vulnerability of Semantic Segmentation Model to Data Transformation
- Open Access
- 31 March 2024
- Published by Institution of Engineering and Technology (IET) in IET Computer Vision
- Vol. 18 (6) , 745-758
Pruning‐guided feature distillation for an efficient transformer‐based pose estimation model
The authors propose a compression strategy for a 3D human pose estimation model based on a transformer which yields high accuracy but increases the model size. This approach involves a pruning‐guided determination of the search range to achieve lightweight pose estimation under limited training time and to identify the optimal model size. In addition, the authors propose a transformer‐based feature distillation (TFD) method, which efficiently exploits the pose estimation model in terms of both model size and accuracy by leveraging transformer architecture characteristics. Pruning‐guided TFD is the first approach for 3D human pose estimation that employs transformer architecture. The proposed approach was tested on various extensive data sets, and the results show that it can reduce the model size by 30% compared to the state‐of‐the‐art while ensuring high accuracy.
- 31 March 2024
- Published by Institution of Engineering and Technology (IET) in IET Computer Vision
- Vol. 18 (6) , 745-758
Open AccessPruning‐guided feature distillation for an efficient transformer‐based pose estimation model
The authors propose a compression strategy for a 3D human pose estimation model based on a transformer which yields high accuracy but increases the model size. This approach involves a pruning‐guided determination of the search range to achieve lightweight pose estimation under limited training time and to identify the optimal model size. In addition, the authors propose a transformer‐based feature distillation (TFD) method, which efficiently exploits the pose estimation model in terms of both model size and accuracy by leveraging transformer architecture characteristics. Pruning‐guided TFD is the first approach for 3D human pose estimation that employs transformer architecture. The proposed approach was tested on various extensive data sets, and the results show that it can reduce the model size by 30% compared to the state‐of‐the‐art while ensuring high accuracy.