Biography
I am Shumpei Takezaki (竹崎 隼平 in Japanse), a Ph.D student at Kyushu University, Fukuoka, JAPAN, under the supervision of Prof. Seiichi Uhicda.
Before starting my Ph.D, I received my undergraduate degree in ECE from the Kagoshima Technical College, Kagoshima, JAPAN.
My research is on generative modeling. I am particularly interested in the applications of generative modeling for medical imaging.
Recent News
- [Reward]: Bridging the Density Gap: Diffusion Model for Stepwise Generation of Dense Cell Images from Sparse Data got ISBI 2026 Best Paper Award-Runner UP (Top 3 papers selected for publication).
- [Paper Acceptance]: Cell Instance Segmentation via Multi-Task Image-to-Image Schrödinger Bridge got accepted to IJCNN 2026.
- [Paper Acceptance]: SCoRe: Clean Image Generation from Diffusion Models Trained on Noisy Images got accepted to IJCNN 2026.
Publications
For a more comprehensive list of publications, please see Publications or visit Google Scholar page.
Cell Instance Segmentation via Multi-Task Image-to-Image Schrödinger Bridge
Published in IJCNN 2026 [Paper]
Citation: Hayato Inoue, Shota Harada, Shumpei Takezaki, Ryoma Bise, "Cell Instance Segmentation via Multi-Task Image-to-Image Schrödinger Bridge", IJCNN 2026
SCoRe: Clean Image Generation from Diffusion Models Trained on Noisy Images
Published in IJCNN 2026 [Paper]
Citation: Yuta Matsuzaki, Seiichi Uchida, Shumpei Takezaki, "SCoRe: Clean Image Generation from Diffusion Models Trained on Noisy Images", IJCNN 2026
VesselFusion: Diffusion Models for Vessel centerline extraction from 3D CT Images
Published in ISBI 2026 [Paper]
Citation: Souichi Mita, Shumpei Takezaki, Ryoma Bise, "VesselFusion: Diffusion Models for Vessel centerline extraction from 3D CT Images", ISBI 2026
Contact
- Address: Human Interface Laboratory, Department of Advanced Information Technology, Kyushu University. 744, Motooka, Nishi-ku, Fukuoka-shi, 819-0395 JAPAN
- TEL: +81-92-802-3574
- E-mail: shumpei.takezaki[at]human.ait.kyushu-u.ac.jp