Abstract | ||
---|---|---|
Computationally removing the motion blur introduced by camera shake or object motion in a captured image remains a challenging task in computational photography. Deblurring methods are often limited by the fixed global exposure time of the image capture process. The post-processing algorithm either must deblur a longer exposure that contains relatively little noise or denoise a short exposure that intentionally removes the opportunity for blur at the cost of increased noise. We present a novel approach of leveraging spatially varying pixel exposures for motion deblurring using next-generation focal-plane sensor-processors along with an end-to-end design of these exposures and a machine learning-based motion-deblurring framework. We demonstrate in simulation and a physical prototype that learned spatially varying pixel exposures (L-SVPE) can successfully deblur scenes while recovering high frequency detail. Our work illustrates the promising role that focal-plane sensor-processors can play in the future of computational imaging. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/ICCP54855.2022.9887786 | 2022 IEEE International Conference on Computational Photography (ICCP) |
Keywords | DocType | ISSN |
Motion deblurring,programmable sensors,in-pixel intelligence,end-to-end optimization,computational imaging | Conference | 2164-9774 |
ISBN | Citations | PageRank |
978-1-6654-5852-8 | 0 | 0.34 |
References | Authors | |
19 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Cindy M. Nguyen | 1 | 0 | 0.34 |
Julien N. P. Martel | 2 | 0 | 0.34 |
Gordon Wetzstein | 3 | 945 | 72.47 |