Deep Optics for Single-shot High-dynamic-range Imaging

by   Christopher A. Metzler, et al.

High-dynamic-range (HDR) imaging is crucial for many computer graphics and vision applications. Yet, acquiring HDR images with a single shot remains a challenging problem. Whereas modern deep learning approaches are successful at hallucinating plausible HDR content from a single low-dynamic-range (LDR) image, saturated scene details often cannot be faithfully recovered. Inspired by recent deep optical imaging approaches, we interpret this problem as jointly training an optical encoder and electronic decoder where the encoder is parameterized by the point spread function (PSF) of the lens, the bottleneck is the sensor with a limited dynamic range, and the decoder is a convolutional neural network (CNN). The lens surface is then jointly optimized with the CNN in a training phase; we fabricate this optimized optical element and attach it as a hardware add-on to a conventional camera during inference. In extensive simulations and with a physical prototype, we demonstrate that this end-to-end deep optical imaging approach to single-shot HDR imaging outperforms both purely CNN-based approaches and other PSF engineering approaches.



There are no comments yet.


page 2

page 4

page 5

page 7

page 9


End-to-End Hyperspectral-Depth Imaging with Learned Diffractive Optics

To extend the capabilities of spectral imaging, hyperspectral and depth ...

Learning Wavefront Coding for Extended Depth of Field Imaging

The depth of field constitutes an important quality factor of imaging sy...

Miniscope3D: optimized single-shot miniature 3D fluorescence microscopy

Miniature fluorescence microscopes are a standard tool in systems biolog...

Video Reconstruction from a Single Motion Blurred Image using Learned Dynamic Phase Coding

Video reconstruction from a single motion-blurred image is a challenging...

Universal and Flexible Optical Aberration Correction Using Deep-Prior Based Deconvolution

High quality imaging usually requires bulky and expensive lenses to comp...

MantissaCam: Learning Snapshot High-dynamic-range Imaging with Perceptually-based In-pixel Irradiance Encoding

The ability to image high-dynamic-range (HDR) scenes is crucial in many ...

Deep High Dynamic Range Imaging with Large Foreground Motions

This paper proposes the first non-flow-based deep framework for high dyn...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.