End-to-end optimization of optics and image processing for achromatic extended depth of field and super-resolution imaging
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 …
image processing algorithm are tuned to get good image reproduction. In contrast to this …
Deep optics for monocular depth estimation and 3d object detection
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 …
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
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 …
contrast, color fidelity), and practical considerations such as cost, form factor, and weight …
Deep optics for single-shot high-dynamic-range imaging
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 …
HDR images with a single shot remains a challenging problem. Whereas modern deep …
Deep learning for camera data acquisition, control, and image estimation
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 …
a camera is first to capture visual information and second to form an image. Conventionally …
Spectral tomographic imaging with aplanatic metalens
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 …
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.
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 …
interact with the world–be that in our personal devices, assistive robotics, or self-driving …
High-quality computational imaging through simple lenses
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 …
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
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 …
advent of deep learning, several approaches for monocular depth estimation have been …
do: A differentiable engine for deep lens design of computational imaging systems
Computational imaging systems algorithmically post-process acquisition images either to
reveal physical quantities of interest or to increase image quality, eg, deblurring. Designing …
reveal physical quantities of interest or to increase image quality, eg, deblurring. Designing …