Image denoising system and method
View Patent ↗A method, computer program product, and computer system for identifying a first portion of a facial image in a first image, wherein the first portion includes noise. A corresponding portion of the facial image is identified in a second image, wherein the corresponding portion includes less noise than the first portion. One or more filter parameters of the first portion are determined based upon, at least in part, the first portion and the corresponding portion. At least a portion of the noise from the first portion is smoothed based upon, at least in part, the one or more filter parameters. At least a portion of face specific details from the corresponding portion is added to the first portion.
1. A computer-implemented method comprising:
identifying, by a computing device, a first portion of a target object in a first image captured under a first environmental condition, wherein the first portion includes noise resulting, at least in part, from the first environmental condition;
identifying a corresponding portion of the same target object or a similar target object in a separately captured second image, captured under a second environmental condition different than the first environmental condition, wherein the corresponding portion includes less noise than the first portion resulting, at least in part, from the second environmental condition;
smoothing at least a portion of the noise from the first portion; and
adding at least a portion of specific details from the corresponding portion to the first portion.
2. The computer-implemented method of claim 1 , wherein the first portion is a facial portion and the corresponding portion is a corresponding facial portion.
3. The computer-implemented method of claim 1 , further including determining a noise level across the first portion and the corresponding portion, wherein the smoothing is based upon, at least in part, the noise level.
4. The computer-implemented method of claim 1 , wherein smoothing includes a bilateral filter.
5. The computer-implemented method of claim 1 , further comprising:
detecting one or more faces in a plurality of images, wherein the plurality of images include at least one of the first image and the second image;
clustering the one or more faces; and
aligning at least a portion of the one or more faces in the plurality of images using one or more facial landmarks.
6. The computer-implemented method of claim 1 , wherein adding the at least the portion of the specific details from the corresponding portion to the first portion includes decomposing at least the corresponding portion to a base layer and a detail layer.
7. The computer-implemented method of claim 1 , further comprising modeling a detail patch of at least one of the first portion and the corresponding portion with a non-parametric Markov random field.
8. The computer-implemented method of claim 7 , further comprising solving the non-parametric Markov random field with a texture optimization framework.
9. A computing system including a processor and a memory configured to perform operations comprising:
identifying a first portion of a target in a first image captured under a first environmental condition, wherein the first portion includes noise resulting, at least in part, from the first environmental condition;
identifying a corresponding portion of the target in a separately captured second image captured under a second environmental condition different than the first environmental condition, wherein the corresponding portion includes less noise than the first portion resulting, at least in part, from the second environmental condition;
smoothing at least a portion of the noise from the first portion; and
adding at least a portion of specific details from the corresponding portion to the first portion.
10. The computer system of claim 9 , wherein the first portion is a facial portion and the corresponding portion is a corresponding facial portion.
11. The computing system of claim 9 , wherein smoothing includes a bilateral filter.
12. The computing system of claim 9 , further comprising:
detecting one or more faces in a plurality of images, wherein the plurality of images include at least one of the first image and the second image;
clustering the one or more faces; and
aligning at least a portion of the one or more faces in the plurality of images using one or more facial landmarks.
13. The computing system of claim 9 , wherein adding the at least portion of specific details from the corresponding portion to the first portion includes decomposing at least the corresponding portion to a base layer and a detail layer.
14. The computing system of claim 9 , further comprising modeling a detail patch of at least one of the first portion and the corresponding portion with a non-parametric Markov random field.
15. The computing system of claim 14 , further comprising solving the non-parametric Markov random field with a texture optimization framework.
16. A computer program product residing on a computer readable non-transitory storage medium having a plurality of instructions stored thereon which, when executed by a processor, cause the processor to perform operations comprising:
identifying a first portion of a target in a first image captured under a first environmental condition, wherein the first portion includes noise resulting, at least in part, from the first environmental condition;
identifying a corresponding portion of the target in a separately captured second image, captured under a second environmental condition different than the first environmental condition, wherein the corresponding portion includes less noise than the first portion resulting, at least in part, from the second environmental condition;
smoothing at least a portion of the noise from the first portion; and
adding at least a portion of specific details from the corresponding portion to the first portion.
17. The computer program product of claim 16 , wherein the first portion is a facial portion and the corresponding portion is a corresponding facial portion.
18. The computer program product of claim 16 , wherein smoothing includes a bilateral filter.
19. The computer program product of claim 16 , wherein the operations further comprise:
detecting one or more faces in a plurality of images, wherein the plurality of images include at least one of the first image and the second image;
clustering the one or more faces; and
aligning at least a portion of the one or more faces in the plurality of images using one or more facial landmarks.
20. The computer program product of claim 16 , wherein adding the at least portion of specific details from the corresponding portion to the first portion includes decomposing at least the corresponding portion to a base layer and a detail layer.