At the intersection of optics and deep learning: statistical inference, computing, and inverse design
Deep learning has been revolutionizing information processing in many fields of science
and engineering owing to the massively growing amounts of data and the advances in deep …
and engineering owing to the massively growing amounts of data and the advances in deep …
Neural nano-optics for high-quality thin lens imaging
Nano-optic imagers that modulate light at sub-wavelength scales could enable new
applications in diverse domains ranging from robotics to medicine. Although metasurface …
applications in diverse domains ranging from robotics to medicine. Although metasurface …
[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 …
Differentiable compound optics and processing pipeline optimization for end-to-end camera design
Most modern commodity imaging systems we use directly for photography—or indirectly rely
on for downstream applications—employ optical systems of multiple lenses that must …
on for downstream applications—employ optical systems of multiple lenses that must …
Single-shot hyperspectral-depth imaging with learned diffractive optics
Imaging depth and spectrum have been extensively studied in isolation from each other for
decades. Recently, hyperspectral-depth (HS-D) imaging emerges to capture both …
decades. Recently, hyperspectral-depth (HS-D) imaging emerges to capture both …
Depth from defocus with learned optics for imaging and occlusion-aware depth estimation
Monocular depth estimation remains a challenging problem, despite significant advances in
neural network architectures that leverage pictorial depth cues alone. Inspired by depth from …
neural network architectures that leverage pictorial depth cues alone. Inspired by depth from …
Flare7k: A phenomenological nighttime flare removal dataset
Artificial lights commonly leave strong lens flare artifacts on images captured at night.
Nighttime flare not only affects the visual quality but also degrades the performance of vision …
Nighttime flare not only affects the visual quality but also degrades the performance of vision …
Curriculum learning for ab initio deep learned refractive optics
Deep optical optimization has recently emerged as a new paradigm for designing
computational imaging systems using only the output image as the objective. However, it …
computational imaging systems using only the output image as the objective. However, it …
HDR video reconstruction: A coarse-to-fine network and a real-world benchmark dataset
High dynamic range (HDR) video reconstruction from sequences captured with alternating
exposures is a very challenging problem. Existing methods often align low dynamic range …
exposures is a very challenging problem. Existing methods often align low dynamic range …
Deep optics for video snapshot compressive imaging
Video snapshot compressive imaging (SCI) aims to capture a sequence of video frames with
only a single shot of a 2D detector, whose backbones rest in optical modulation patterns …
only a single shot of a 2D detector, whose backbones rest in optical modulation patterns …