Single-shot autofocus via adaptive foveation from global perception to local focus
• Proposes a single-shot autofocus network that jointly models global scene perception and local sharpness features. • Introduces an adaptive foveation mechanism to balance large-scale contextual information and fine-grained focus cues. • Employs sharpness-guided feature modulation to enhance informative regions during defocus regression. • Experiments on biological and industrial chip datasets demonstrate accurate and stable defocus estimation under varying defocus levels and texture complexity.
Authors
- Kaining Yang (ORCID: https://orcid.org/0009-0005-3463-8218)
- Tong Zhang (ORCID: https://orcid.org/0009-0001-8538-3738)
- Fei Liu
- Jinpeng Liu (ORCID: https://orcid.org/0000-0002-3071-4499)
- Pingli Han
- Xiyuan Luo
- Xue Dong
- Zheng Liu
- Qichen Zhang
Institutions
- Xidian University (CN)
- Xi’an University (CN)
- Beijing Jingshida Electromechanical Equipment Research Institute (CN)
Publication Details
- Journal
- Optics and Lasers in Engineering
- Published
- 2026-05-31
- DOI
- https://doi.org/10.1016/j.optlaseng.2026.109899
- Primary Topic
- Image Processing Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation
- Education Department of Shaanxi Province
- National University's Basic Research Foundation of China