Auto-Tuning Structured Light by
Optical Stochastic Gradient Descent

Wenzheng Chen*
Parsa Mirdehghan*
Sanja Filder
Kiriakos N. Kutulakos

University of Toronto
CVPR 2020

* equal contribution

We present Optical SGD, a hardware-in-the-loop computational imaging technique for optimizing active imaging systems on the fly.

We consider the problem of optimizing the performance of an active imaging system by automatically discovering the illuminations it should use, and the way to decode them. Our approach tackles two seemingly incompatible goals: (1) "tuning" the illuminations and decoding algorithm precisely to the devices at hand---to their optical transfer functions, non-linearities, spectral responses, image processing pipelines---and (2) doing so without modeling or calibrating the system; without modeling the scenes of interest; and without prior training data. The key idea is to formulate a stochastic gradient descent (SGD) optimization procedure that puts the actual system in the loop: projecting patterns, capturing images, and calculating the gradient of expected reconstruction error. We apply this idea to structured-light triangulation to "auto-tune" several devices---from smartphones and laser projectors to advanced computational cameras. Our experiments show that despite being modelfree and automatic, optical SGD can boost system 3D accuracy substantially over state-of-the-art coding schemes.


Wenzheng Chen, Parsa Mirdehghan,
Sanja Filder, Kiriakos N. Kutulakos

Auto-Tuning Structured Light by
Optical Stochastic Gradient Descent

Proc. IEEE/CVF CVPR 2020

[Supplementary Document]
[Supplementary Slides with Videos (pptx)]
[Supplementary Slides (PDF)]

Please address correspondence regarding this paper to Wenzheng Chen.

Webpage template from: © Richard Zhang