US 12,755,353 B2 · Artificial intelligence deep learning for controlling aliasing artifacts

Abstract

A method includes receiving a degraded image including aliasing artifacts and inputting the degraded image to an image enhancement network. This method also includes processing, using the image enhancement network, the degraded image to remove one or more of the aliasing artifacts and outputting, by the image enhancement network, a restored high-quality image. Another method includes obtaining a high-quality image of an environment and generating at least one degraded image of the environment by performing an aliasing artifact simulation on the obtained high-quality image. Performing the aliasing artifact simulation includes (i) performing a broken line artifact simulation to introduce one or more broken line artifacts on one or more objects in the environment of the high-quality image and/or (ii) performing a jaggy artifact simulation to introduce jaggy edges to one or more other objects in the environment of the high-quality image.

Claims20

Dependent claims

A method comprising:

receiving a degraded image comprising aliasing artifacts;
inputting the degraded image to an image enhancement network, wherein the image enhancement network is trained by:
obtaining a high-quality image of an environment;
and
performing an aliasing artifact simulation on the obtained high-quality image comprising at least one of:
performing a broken line artifact simulation using affine transform and interpolation to introduce one or more broken line artifacts on one or more objects in the environment of the high-quality image;
and
performing a jaggy artifact simulation using a detection map to introduce jaggy edges to one or more other objects in the environment of the high-quality image;
processing, using the image enhancement network, the degraded image to remove one or more of the aliasing artifacts;
and
outputting, by the image enhancement network, a restored high-quality image.

8 more elements

An electronic device comprising:

at least one processing device configured to:
receive a degraded image comprising aliasing artifacts;
input the degraded image to an image enhancement network, wherein to train the image enhancement network:
a high-quality image of an environment is obtained;
and
an aliasing artifact simulation is performed on the obtained high-quality image comprising at least one of:
a broken line artifact simulation using affine transform and interpolation to introduce one or more broken line artifacts on one or more objects in the environment of the high-quality image;
and
a jaggy artifact simulation using a detection map to introduce jaggy edges to one or more other objects in the environment of the high-quality image;
process, using the image enhancement network, the degraded image to remove one or more of the aliasing artifacts;
and
output, by the image enhancement network, a restored high-quality image.

9 more elements

A non-transitory machine readable medium containing instructions that when executed cause at least one processor of an electronic device to:

receive a degraded image comprising aliasing artifacts;
input the degraded image to an image enhancement network, wherein to train the image enhancement network:
a high-quality image of an environment is obtained;
and
an aliasing artifact simulation is performed on the obtained high-quality image comprising at least one of:
a broken line artifact simulation using affine transform and interpolation to introduce one or more broken line artifacts on one or more objects in the environment of the high-quality image;
and
a jaggy artifact simulation using a detection map to introduce jaggy edges to one or more other objects in the environment of the high-quality image;
process, using the image enhancement network, the degraded image to remove one or more of the aliasing artifacts;
and
output, by the image enhancement network, a restored high-quality image.

8 more elements

Dependencies are inferred from the claim text.

Artificial intelligence deep learning for controlling aliasing artifacts

Life of this patent

Artificial intelligence deep learning for controlling aliasing artifacts

Life of this patent

Abstract

Claims20