Depth from Defocus with Learned Optics for Imaging and Occlusion-aware Depth Estimation

• Published in: IEEE International Conference on Computational Photography pp. 1 - 12
• Main Authors: Ikoma, Hayato, Nguyen, Cindy M., Metzler, Christopher A., Peng, Yifan, Wetzstein, Gordon
• Format: Conference Proceeding
• Language: English
• Published: IEEE 23.05.2021
• Subjects: Apertures; Computational modeling; Computational Optics; Computational Photography; Estimation; Neural networks; Optics; Photography; Prototypes

Monocular depth estimation remains a challenging problem, despite significant advances in neural network architectures that leverage pictorial depth cues alone. Inspired by depth from defocus and emerging point spread function engineering approaches that optimize programmable optics end-to-end with...