Learning to Estimate Kernel Scale and Orientation of Defocus Blur with Asymmetric Coded Aperture
This addresses the issue of inconsistent in-focus imagery for machine vision systems, but it appears incremental as it builds on existing methods with specific improvements.
The paper tackles the problem of defocus blur degrading machine vision systems by proposing a deep-learning framework to estimate kernel scale and orientation for rapid lens focus adjustment, achieving effectiveness as demonstrated in experiments.
Consistent in-focus input imagery is an essential precondition for machine vision systems to perceive the dynamic environment. A defocus blur severely degrades the performance of vision systems. To tackle this problem, we propose a deep-learning-based framework estimating the kernel scale and orientation of the defocus blur to adjust lens focus rapidly. Our pipeline utilizes 3D ConvNet for a variable number of input hypotheses to select the optimal slice from the input stack. We use random shuffle and Gumbel-softmax to improve network performance. We also propose to generate synthetic defocused images with various asymmetric coded apertures to facilitate training. Experiments are conducted to demonstrate the effectiveness of our framework.