Learning Spatially Varying Pixel Exposures for Motion Deblurring
This addresses motion blur in computational photography, offering a novel hardware-software co-design approach that is not incremental but leverages emerging sensor technology.
The paper tackles motion blur in images by introducing learned spatially varying pixel exposures (L-SVPE) using focal-plane sensor-processors, demonstrating in simulation and a prototype that it successfully deblurs scenes while recovering high-frequency details.
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.