End-to-end optimization of optics and image processing for achromatic extended depth of field and super-resolution imaging

V Sitzmann, S Diamond, Y Peng, X Dun… - ACM Transactions on …, 2018 - dl.acm.org
In typical cameras the optical system is designed first; once it is fixed, the parameters in the
image processing algorithm are tuned to get good image reproduction. In contrast to this …

Deep optics for monocular depth estimation and 3d object detection

J Chang, G Wetzstein - Proceedings of the IEEE/CVF …, 2019 - openaccess.thecvf.com
Depth estimation and 3D object detection are critical for scene understanding but remain
challenging to perform with a single image due to the loss of 3D information during image …

[PDF][PDF] End-to-end complex lens design with differentiable ray tracing

Q Sun, C Wang, F Qiang, D **ong, H Wolfgang - ACM Trans. Graph, 2021 - vccimaging.org
Cameras are designed with a complicated tradeoff between image quality (eg sharpness,
contrast, color fidelity), and practical considerations such as cost, form factor, and weight …

Deep optics for single-shot high-dynamic-range imaging

CA Metzler, H Ikoma, Y Peng… - Proceedings of the …, 2020 - openaccess.thecvf.com
Abstract High-dynamic-range (HDR) imaging is crucial for many applications. Yet, acquiring
HDR images with a single shot remains a challenging problem. Whereas modern deep …

Deep learning for camera data acquisition, control, and image estimation

DJ Brady, L Fang, Z Ma - Advances in Optics and Photonics, 2020 - opg.optica.org
We review the impact of deep-learning technologies on camera architecture. The function of
a camera is first to capture visual information and second to form an image. Conventionally …

Spectral tomographic imaging with aplanatic metalens

C Chen, W Song, JW Chen, JH Wang… - Light: Science & …, 2019 - nature.com
Tomography is an informative imaging modality that is usually implemented by mechanical
scanning, owing to the limited depth-of-field (DOF) in conventional systems. However, recent …

[PDF][PDF] Learned large field-of-view imaging with thin-plate optics.

Y Peng, Q Sun, X Dun, G Wetzstein, W Heidrich… - ACM Trans …, 2019 - researchgate.net
Modern imaging techniques have equipped us with powerful capabilities to record and
interact with the world–be that in our personal devices, assistive robotics, or self-driving …

High-quality computational imaging through simple lenses

F Heide, M Rouf, MB Hullin, B Labitzke… - ACM Transactions on …, 2013 - dl.acm.org
Modern imaging optics are highly complex systems consisting of up to two dozen individual
optical elements. This complexity is required in order to compensate for the geometric and …

Depth estimation from a single image using deep learned phase coded mask

H Haim, S Elmalem, R Giryes… - IEEE Transactions …, 2018 - ieeexplore.ieee.org
Depth estimation from a single image is a well-known challenge in computer vision. With the
advent of deep learning, several approaches for monocular depth estimation have been …

do: A differentiable engine for deep lens design of computational imaging systems

C Wang, N Chen, W Heidrich - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Computational imaging systems algorithmically post-process acquisition images either to
reveal physical quantities of interest or to increase image quality, eg, deblurring. Designing …