Beautification techniques for 3D data in a messaging system

1. A method, comprising:

receiving, at a client device, a selection of a selectable graphical item from a plurality of selectable graphical items, the selectable graphical item comprising an augmented reality content generator for applying a 3D effect, the 3D effect including at least one beautification operation, the beautification operation comprising modifying image data, the image data including a region corresponding to a representation of a face, the modifying comprising an effect that retouches the representation of the face, the beautification operation further comprising using a machine learning model for at least one of smoothing blemishes or preserving facial skin texture;

capturing image data and depth data using a camera of the client device,

applying, to the image data and the depth data, the 3D effect including the at least one beautification operation based at least in part on the augmented reality content generator, the beautification operation being performed as part of applying the 3D effect, the applying, to the image data and the depth data, the 3D effect comprising:

generating a depth map using at least the depth data,

generating a segmentation mask based at least on the image data, and

performing background inpainting and blurring of the image data using at least the segmentation mask to generate background inpainted image data;

generating a 3D message based at least in part on the applied 3D effect including the at least one beautification operation; and

rendering a view of the 3D message based at least in part on the applied 3D effect including the at least one beautification operation.

2. The method of claim 1 , wherein applying, to the image data and the depth data, the 3D effect comprises:

generating a packed depth map based at least in part on the depth map, the generating the packed depth map comprising:

converting a single channel floating point texture to a raw depth map, and

generating multiple channels based at least in part on the raw depth map; and

performing the beautification operation on a region of at least the image data including facial image data, the beautification operation comprising at least one of smoothing, lighting adjustment, or color modification.

3. The method of claim 1 , wherein the beautification operation further comprises utilizing a portrait segmentation mask when applying the beautification operation to the image data including the region corresponding to the representation of the face, and the machine learning model comprises one of a convolutional neural network or a generative adversarial network.

4. The method of claim 1 , further comprising:

determining a depth map based at least in part on the depth data;

generating a depth inpainting mask corresponding to a region of the depth map including facial depth data; and

performing depth map inpainting of the depth map using at least the generated depth inpainting mask.

5. The method of claim 4 , wherein the depth map comprises a packed depth map.

6. The method of claim 5 , wherein the packed depth map has a lower resolution than the image data.

7. The method of claim 4 , further comprising:

generating a normal map of the depth map for applying a lighting effect to facial image data of the image data; and

applying the lighting effect to the facial image data based at least in part on the normal map.

8. The method of claim 7 , wherein the lighting effect comprises at least two different colors, a first color from the two different colors being applied to a first portion of the facial image data, and a second color from the two different colors being applied to a second image of the facial image data.

9. The method of claim 1 , further comprising:

causing display of an interface comprising the plurality of selectable graphical items, each selectable graphical item corresponding to a respective augmented reality content generator of a set of augmented reality content generators.

10. The method of claim 9 , further comprising:

receiving a swipe gesture via a touch screen of the client device; and

in response to receiving the swipe gesture, causing navigation through the plurality of selectable graphical items.

11. A system comprising:

a processor; and

a memory including instructions that, when executed by the processor, cause the processor to perform operations comprising:

receiving, at a client device, a selection of a selectable graphical item from a plurality of selectable graphical items, the selectable graphical item comprising an augmented reality content generator for applying a 3D effect, the 3D effect including at least one beautification operation, the beautification operation comprising modifying image data, the image data including a region corresponding to a representation of a face, the modifying comprising an effect that retouches the representation of the face, the beautification operation further comprising using a machine learning model for at least one of smoothing blemishes or preserving facial skin texture;

capturing image data and depth data using a camera of the client device;

applying, to the image data and the depth data, the 3D effect including the at least one beautification operation based at least in part on the augmented reality content generator, the beautification operation being performed as part of applying the 3D effect, the applying, to the image data and the depth data, the 3D effect comprising:

generating a depth map using at least the depth data,

generating a segmentation mask based at least on the image data, and

performing background inpainting and blurring of the image data using at least the segmentation mask to generate background inpainted image data;

generating a 3D message based at least in part on the applied 3D effect including the at least one beautification operation; and

rendering a view of the 3D message based at least in part on the applied 3D effect including the at least one beautification operation.

12. The system of claim 11 , wherein applying, to the image data and the depth data, the 3D effect comprises:

performing the beautification operation on a region of at least the image data including facial image data, the beautification operation comprising at least one of smoothing, lighting adjustment, or color modification.

13. The system of claim 11 , wherein the beautification operation further comprises utilizing a portrait segmentation mask when applying the beautification operation to the image data including the region corresponding to the representation of the face.

14. The system of claim 11 , wherein the operations further comprise:

determining a depth map based at least in part on the depth data;

generating a depth inpainting mask corresponding to a region of the depth map including facial depth data; and

performing depth map inpainting of the depth map using at least the generated depth inpainting mask.

15. The system of claim 14 , wherein the depth map comprises a packed depth map.

16. The system of claim 15 , wherein the packed depth map has a lower resolution than the image data.

17. The system of claim 14 , wherein the operations further comprise:

generating a normal map of the depth map for applying a lighting effect to facial image data of the image data; and

applying the lighting effect to the facial image data based at least in part on the normal map.

18. The system of claim 17 , wherein the lighting effect comprises at least two different colors, a first color from the two different colors being applied to a first portion of the facial image data, and a second color from the two different colors being applied to a second image of the facial image data.

19. The system of claim 11 , wherein the operations further comprise:

causing display of an interface comprising the plurality of selectable graphical items, each selectable graphical item corresponding to a respective augmented reality content generator of a set of augmented reality content generators.

20. A non-transitory computer-readable medium comprising instructions, which when executed by a computing device, cause the computing device to perform operations comprising:

receiving, at a client device, a selection of a selectable graphical item from a plurality of selectable graphical items, the selectable graphical item comprising an augmented reality content generator for applying a 3D effect, the 3D effect including at least one beautification operation, the beautification operation comprising modifying image data, the image data including a region corresponding to a representation of a face, the modifying comprising an effect that retouches the representation of the face, the beautification operation further comprising using a machine learning model for at least one of smoothing blemishes or preserving facial skin texture;

capturing image data and depth data using a camera of the client device;

applying, to the image data and the depth data, the 3D effect including the at least one beautification operation based at least in part on the augmented reality content generator, the beautification operation being performed as part of applying the 3D effect, the applying, to the image data and the depth data, the 3D effect comprising:

generating a depth map using at least the depth data,

generating a segmentation mask based at least on the image data, and

performing background inpainting and blurring of the image data using at least the segmentation mask to generate background inpainted image data;

generating a 3D message based at least in part on the applied 3D effect including the at least one beautification operation; and

rendering a view of the 3D message based at least in part on the applied 3D effect including the at least one beautification operation.