Deep Learning for Camera Autofocus
| Autor: | David J. Brady, Zhan Ma, Qian Huang, Ming Cheng, Chengyu Wang |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Autofocus
Computer science business.industry Image quality Deep learning ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 020206 networking & telecommunications 02 engineering and technology Pipeline (software) Computer Science Applications Image (mathematics) law.invention Focus stacking Computational Mathematics law Position (vector) Signal Processing 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Artificial intelligence Focus (optics) business |
| Zdroj: | IEEE Transactions on Computational Imaging. 7:258-271 |
| ISSN: | 2334-0118 2573-0436 |
| DOI: | 10.1109/tci.2021.3059497 |
| Popis: | Most digital cameras use specialized autofocus sensors, such as phase detection, lidar or ultrasound, to directly measure focus state. However, such sensors increase cost and complexity without directly optimizing final image quality. This paper proposes a new pipeline for image-based autofocus and shows that neural image analysis finds focus 5-10x faster than traditional contrast enhancement. We achieve this by learning the direct mapping between an image and its focus position. In further contrast with conventional methods, AI methods can generate scene-based focus trajectories that optimize synthesized image quality for dynamic and three dimensional scenes. We propose a focus control strategy that varies focal position dynamically to maximize image quality as estimated from the focal stack. We propose a rule-based agent and a learned agent for different scenarios and show their advantages over other focus stacking methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|