TY - GEN
T1 - Deep Phase Coded Image Prior
AU - Shabtay, Nimrod
AU - Schwartz, Eli
AU - Giryes, Raja
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Phase-coded imaging is a computational imaging scheme designed to tackle tasks such as passive depth estimation and extended depth of field (EDOF) by inserting depth cues during image capture. Most of the current deep learning-based methods for depth estimation or all-in-focus imaging require a training dataset with high-quality depth maps and an optimal focus point at infinity for all-in-focus images. These datasets are difficult to create, often synthetic, and require external graphic software. Thus, limited datasets are being used, limiting the diversity of applicable domains. We propose a new method named 'Deep Phase Coded Image Prior' (DPCIP) for jointly recovering the depth map and all-in-focus image from a coded-phase image using solely the captured image and the optical information of the imaging system. Our approach does not depend on any specific dataset and surpasses prior supervised techniques utilizing the same imaging system. This improvement is achieved through the utilization of a problem formulation based on implicit neural representation (INR) and deep image prior (DIP). Due to our zero-shot method, we overcome the barrier of acquiring accurate ground-truth data of depth maps and all-in-focus images for each new phase-coded system introduced. This allows focusing mainly on developing the imaging system, and not on ground-truth data collection.
AB - Phase-coded imaging is a computational imaging scheme designed to tackle tasks such as passive depth estimation and extended depth of field (EDOF) by inserting depth cues during image capture. Most of the current deep learning-based methods for depth estimation or all-in-focus imaging require a training dataset with high-quality depth maps and an optimal focus point at infinity for all-in-focus images. These datasets are difficult to create, often synthetic, and require external graphic software. Thus, limited datasets are being used, limiting the diversity of applicable domains. We propose a new method named 'Deep Phase Coded Image Prior' (DPCIP) for jointly recovering the depth map and all-in-focus image from a coded-phase image using solely the captured image and the optical information of the imaging system. Our approach does not depend on any specific dataset and surpasses prior supervised techniques utilizing the same imaging system. This improvement is achieved through the utilization of a problem formulation based on implicit neural representation (INR) and deep image prior (DIP). Due to our zero-shot method, we overcome the barrier of acquiring accurate ground-truth data of depth maps and all-in-focus images for each new phase-coded system introduced. This allows focusing mainly on developing the imaging system, and not on ground-truth data collection.
KW - Deep Image Prior
KW - Neural Rendering
KW - Phase-coded Imaging
KW - Physics-based Rendering
UR - http://www.scopus.com/inward/record.url?scp=85203840662&partnerID=8YFLogxK
U2 - 10.1109/ICCP61108.2024.10645026
DO - 10.1109/ICCP61108.2024.10645026
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85203840662
T3 - 2024 IEEE International Conference on Computational Photography, ICCP 2024 - Proceedings
BT - 2024 IEEE International Conference on Computational Photography, ICCP 2024 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 16th IEEE International Conference on Computational Photography, ICCP 2024
Y2 - 22 July 2024 through 24 July 2024
ER -