High quality AR cosmetics simulation via image filtering techniques

1. A computing system comprising:

one or more processors;

one or more non-transitory computer readable media that collectively store instructions that, when executed by the one or more processors, cause the computing system to perform operations, the operations comprising:

obtaining an image of a face;

obtaining material property data associated with a material, wherein the material property data comprises data associated with a mid-tones spectral band;

adjusting a saturation of at least a portion of the image to generate a resulting image;

generating a mid-tones image dataset based at least in part on the resulting image and a base color value, wherein the base color value comprises a color pixel value for at least a portion of the image, wherein the mid-tones image dataset is associated with the mid-tones spectral band;

processing the mid-tones image dataset with the material property data to generate a mid-tones map; and

generating, based at least in part on the mid-tones map, an augmented image that depicts the material applied to the face.

2. The system of claim 1 , wherein generating a mid-tones image dataset comprises:

multiplying the resulting image by the base color value.

3. The system of claim 2 , wherein the base color value comprises a red-green-blue pixel value.

4. The system of claim 1 , wherein generating a mid-tones image dataset comprises:

adjusting one or more image levels based at least in part on a gamma value associated with the material property data.

5. The system of claim 4 , wherein the one or more image levels comprise one or more brightness levels associated with a histogram of brightness from black to white.

6. The system of claim 1 , wherein the operations further comprise:

generating a highlights image dataset, wherein generating the highlights image dataset comprises:

adjusting one or more image levels of the resulting image based on an input black and a gamma value associated with the material property data.

7. The system of claim 1 , wherein the operations further comprise:

adjusting one or more tritones of the resulting image based at least in part on an input gray color associated with the material property data;

adjusting one or more image levels of the resulting image based at least in part on an input gamma value associated with the material property data; and

generating a shadows image dataset based on the resulting image on a weighted base color value associated with a particular region of the image.

8. A computer-implemented method, the method comprising:

obtaining, by a computing system comprising one or more processors, an image, wherein the image comprises a face;

obtaining, by the computing system, material property data associated with a material for application on one or more facial features;

decomposing, by the computing system, the image into a plurality of image datasets respectively associated with a plurality of spectral bands, wherein the plurality of image datasets comprise: a shadows image dataset associated with a shadows spectral band, a highlights image dataset associated with a highlights spectral band, and a mid-tones image dataset associated with a mid-tones spectral band;

processing, by the computing system, the plurality of image datasets and the material property data to generate a plurality of material maps, wherein the plurality of material maps comprise one or more material maps for each respective spectral band of the plurality of spectral bands; and

blending, by the computing system, the plurality of material maps with the image to generate an augmented image.

9. The method of claim 8 , wherein processing the plurality of image datasets and the material property data to generate the plurality of material maps comprises:

processing, by the computing system, the shadows image dataset and material property data associated with the shadows spectral band to generate a first material map;

processing, by the computing system, the highlights image dataset and material property data associated with the highlights spectral band to generate a second material map; and

processing, by the computing system, the mid-tones image dataset and material property data associated with the mid-tones spectral band to generate a third material map.

10. The method of claim 8 , further comprising:

detecting, by the computing system, a location of the one or more facial features of the face.

11. The method of claim 8 , further comprising:

providing, by the computing system, the augmented image via an interface of an augmented reality application.

12. The method of claim 8 , wherein the augmented image is descriptive of a simulation of the material applied to the face.

13. The method of claim 8 , wherein the material is associated with a cosmetic product.

14. The method of claim 8 , wherein the material property data is descriptive of at least one of a color, reflectivity, or opacity associated with the material.

15. The method of claim 8 , wherein the plurality of material maps are associated with the one or more facial features.

16. One or more non-transitory computer-readable media that store instructions that, when executed by one or more processors, cause the one or more processors to perform operations, the operations comprising:

obtaining image data, wherein the image data comprises an object;

obtaining material property data associated with a material for application on the object;

decomposing the image data into a plurality of image datasets respectively associated with a plurality of spectral bands, wherein the plurality of image datasets comprise: a shadows image dataset associated with a shadows spectral band, a highlights image dataset associated with a highlights spectral band, and a mid-tones image dataset associated with a mid-tones spectral band;

processing the plurality of image datasets and the material property data to generate a plurality of material maps, wherein the plurality of material maps comprise one or more material maps for each respective spectral band of the plurality of spectral bands; and

generating an augmented image data based on the plurality of material maps and the image data.

17. The one or more non-transitory computer-readable media of claim 16 , wherein the image data comprises a video from a camera.

18. The one or more non-transitory computer-readable media of claim 16 , further comprising:

providing the augmented image data via a real-time simulation interface provided by an online retailer.

19. The one or more non-transitory computer-readable media of claim 16 , wherein the object comprises a body part.

20. The one or more non-transitory computer-readable media of claim 16 , wherein the operations further comprise:

performing a face tracking technique on the image data to generate face tracking data; and

wherein the augmented image data is generated based at least in part on the face tracking data.