Skip to main content

Differentiable Compound Optics and Processing Pipeline Optimization for End-to-end Camera Design

Author(s): Tseng, Ethan; Mosleh, Ali; Mannan, Fahim; St-Arnaud, Karl; Sharma, Avinash; et al

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr19c6s13t
Full metadata record
DC FieldValueLanguage
dc.contributor.authorTseng, Ethan-
dc.contributor.authorMosleh, Ali-
dc.contributor.authorMannan, Fahim-
dc.contributor.authorSt-Arnaud, Karl-
dc.contributor.authorSharma, Avinash-
dc.contributor.authorPeng, Yifan-
dc.contributor.authorBraun, Alexander-
dc.contributor.authorNowrouzezahrai, Derek-
dc.contributor.authorLalonde, Jean-François-
dc.contributor.authorHeide, Felix-
dc.date.accessioned2023-12-28T16:02:09Z-
dc.date.available2023-12-28T16:02:09Z-
dc.date.issued2021-04en_US
dc.identifier.citationTseng, Ethan, Ali Mosleh, Fahim Mannan, Karl St-Arnaud, Avinash Sharma, Yifan Peng, Alexander Braun, Derek Nowrouzezahrai, Jean-Francois Lalonde, and Felix Heide. "Differentiable Compound Optics and Processing Pipeline Optimization for End-to-end Camera Design." ACM Transactions on Graphics (TOG) 40, no. 2 (2021): 1-19. doi:10.1145/3446791en_US
dc.identifier.issn0730-0301-
dc.identifier.urihttps://light.cs.princeton.edu/wp-content/uploads/2021/02/DeepCompoundOptics.pdf-
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/pr19c6s13t-
dc.description.abstractMost modern commodity imaging systems we use directly for photography—or indirectly rely on for downstream applications—employ optical systems of multiple lenses that must balance deviations from perfect optics, manufacturing constraints, tolerances, cost, and footprint. Although optical designs often have complex interactions with downstream image processing or analysis tasks, today’s compound optics are designed in isolation from these interactions. Existing optical design tools aim to minimize optical aberrations, such as deviations from Gauss’ linear model of optics, instead of application-specific losses, precluding joint optimization with hardware image signal processing (ISP) and highly parameterized neural network processing. In this article, we propose an optimization method for compound optics that lifts these limitations. We optimize entire lens systems jointly with hardware and software image processing pipelines, downstream neural network processing, and application-specific end-to-end losses. To this end, we propose a learned, differentiable forward model for compound optics and an alternating proximal optimization method that handles function compositions with highly varying parameter dimensions for optics, hardware ISP, and neural nets. Our method integrates seamlessly atop existing optical design tools, such as Zemax. We can thus assess our method across many camera system designs and end-to-end applications. We validate our approach in an automotive camera optics setting—together with hardware ISP post processing and detection—outperforming classical optics designs for automotive object detection and traffic light state detection. For human viewing tasks, we optimize optics and processing pipelines for dynamic outdoor scenarios and dynamic low-light imaging. We outperform existing compartmentalized design or fine-tuning methods qualitatively and quantitatively, across all domain-specific applications tested.en_US
dc.format.extent1 - 19en_US
dc.language.isoen_USen_US
dc.relation.ispartofACM Transactions on Graphicsen_US
dc.rightsAuthor's manuscripten_US
dc.titleDifferentiable Compound Optics and Processing Pipeline Optimization for End-to-end Camera Designen_US
dc.typeJournal Articleen_US
dc.identifier.doi10.1145/3446791-
dc.identifier.eissn1557-7368-
pu.type.symplectichttp://www.symplectic.co.uk/publications/atom-terms/1.0/journal-articleen_US

Files in This Item:
File Description SizeFormat 
DeepCompoundOptics.pdf45.39 MBAdobe PDFView/Download


Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.