Chromatic Aberration Correction Using Cross-Channel Prior in Shearlet Domain

Achromatic Imaging Systems with Flat Lenses Enabled by Deep Learning

“…Deconvolution methods with TLC correction priors can correct TLC and TAC simultaneously. Suggested TLC correction priors use cross-channel gradients or cross-channel shearlet transform . These traditional methods do not rely on ground truth images and therefore cannot report metric scores on real images.…”

“…Novel nanostructure design has introduced the ability to correct the chromatic aberration of metalenses − and of diffractive lenses. ,− Both have been shown to have fundamental performance limitations. , Another way to tackle chromatic aberration is by image processing . Chromatic aberration caused by single-ball lenses has been corrected to some extent by an image processing algorithm . With the rapid advancement of machine learning, deep-learning models have demonstrated superior performance compared to traditional image restoration methods. − Recent works show a step forward toward facing flat lens challenges by applying algorithms to reduce chromatic aberrations of a hybrid diffractive–refractive imaging system using images that were captured indoors in laboratory conditions. ,, Other works combined computational imaging with advanced meta-optics designs , and were able to reduce chromatic aberrations in the imaging of miniature samples under laboratory conditions.…”

“…29 Chromatic aberration caused by single-ball lenses has been corrected to some extent by an image processing algorithm. 30 With the rapid advancement of machine learning, deep-learning models have demonstrated superior performance compared to traditional image restoration methods. 31−33 Recent works show a step forward toward facing flat lens challenges by applying algorithms to reduce chromatic aberrations of a hybrid diffractive−refractive imaging system using images that were captured indoors in laboratory conditions.…”

“…Suggested TLC correction priors use cross-channel gradients 29 or cross-channel shearlet transform. 30 These traditional methods do not rely on ground truth images and therefore cannot report metric scores on real images. Importantly, such methods become less efficient in low SNR scenarios, as they tend to enhance the noise.…”

“…Chromatic aberration caused by single-ball lenses has been corrected to some extent by an image processing algorithm . With the rapid advancement of machine learning, deep-learning models have demonstrated superior performance compared to traditional image restoration methods. − Recent works show a step forward toward facing flat lens challenges by applying algorithms to reduce chromatic aberrations of a hybrid diffractive–refractive imaging system using images that were captured indoors in laboratory conditions. ,, Other works combined computational imaging with advanced meta-optics designs , and were able to reduce chromatic aberrations in the imaging of miniature samples under laboratory conditions. Tseng et al used a deep-learning approach to jointly optimize a metasurface design and its corresponding deconvolution algorithm based on point-spread-function (PSF) estimation and simulated images.…”