Deep Eyes: Binocular Depth-from-Focus on Focal Stack Pairs
This work addresses depth inference in computer vision by integrating traditionally separate cues, offering a more human-like approach for applications like robotics or augmented reality, though it is incremental as it builds on existing networks.
The paper tackles the problem of 3D depth perception by unifying binocular stereo and monocular focus cues, using a learning-based technique with focal stack pairs as input. The result is a method that outperforms state-of-the-art approaches in both accuracy and speed, effectively emulating human vision systems.
Human visual system relies on both binocular stereo cues and monocular focusness cues to gain effective 3D perception. In computer vision, the two problems are traditionally solved in separate tracks. In this paper, we present a unified learning-based technique that simultaneously uses both types of cues for depth inference. Specifically, we use a pair of focal stacks as input to emulate human perception. We first construct a comprehensive focal stack training dataset synthesized by depth-guided light field rendering. We then construct three individual networks: a Focus-Net to extract depth from a single focal stack, a EDoF-Net to obtain the extended depth of field (EDoF) image from the focal stack, and a Stereo-Net to conduct stereo matching. We show how to integrate them into a unified BDfF-Net to obtain high-quality depth maps. Comprehensive experiments show that our approach outperforms the state-of-the-art in both accuracy and speed and effectively emulates human vision systems.