Exact Blur Measure Outperforms Conventional Learned Features for Depth Finding
This work addresses computational challenges in image-based depth estimation for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of depth estimation from single images by developing an exact blur measurement method for Depth From Defocus (DFD) techniques, which experimentally outperforms conventional learned features with improved error performance.
Image analysis methods that are based on exact blur values are faced with the computational complexities due to blur measurement error. This atmosphere encourages scholars to look for handcrafted and learned features for finding depth from a single image. This paper introduces a novel exact realization for blur measures on digital images and implements it on a new measure of defocus Gaussian blur at edge points in Depth From Defocus (DFD) methods with the potential to change this atmosphere. The experiments on real images indicate superiority of the proposed measure in error performance over conventional learned features in the state-of the-art single image based depth estimation methods.