Toma Okugawa 奥河 董馬
A programmer building low-light computer vision with classical Retinex, on-device AI apps, and the web.
I’m a third-year student in the Information Science and Technology Department at NIT Yuge College, a KOSEN in Kamijima, Ehime, Japan. I research low-light image enhancement based on classical Retinex theory, and I have published the code and evaluation results of SD-Retinex, a training-free method that is fast even on a CPU. Building on my research, I make Kyudo AI, an app that scores kyudo form on the phone, and Beacon, which clarifies inspection footage from dark places offline. I started programming in earnest with Python in 2025 and now also write Dart (Flutter) and TypeScript.
Now — Building the Kyudo AI app in Flutter, with a paper to present at IEEE GCCE 2026.
Featured projects
- SD-Retinex 2026
A training-free low-light enhancement method designed around the sigmoid derivative, fast on a CPU. The paper, code and evaluation results are public.
- Kyudo AI 2026
A Flutter app that scores kyudo (Japanese archery) form with pose estimation that runs on the phone, and keeps hit records and club messages in one place.
- Beacon 2026
Built on SD-Retinex, Beacon clarifies inspection footage from places light cannot reach, offline, on an existing PC without a GPU.