Asymmetric stereo with catadioptric lens: High quality image generation for intelligent robot

Abstract

In this paper, we design a new asymmetric stereo system with catadioptric lens for intelligent robot. The main benefit of catadioptric lens is long focal length with short and light lens body compared to common telephoto lenses. However, there are two critical shortcomings in catadioptric lens: narrow depth of field (DOF) and ring bokeh. Narrow DOF is a property of telephoto lens and ring bokeh stems from its special inner structure. With a help of conventional compound lens, we propose a method to overcome limitations of catadioptric lens via defocus estimation using multi-scale patch matching. Experimental results demonstrate that our approach recovers all-in-focus images from a new proposed asymmetric stereo system. Also, we show various applications based on the estimated defocus map and the recovered image. Our new system can be helpful for constructing robust vision system for intelligent robot.