Systems and methods for capturing images with augmented-reality effects

1. A method, by a computing device, comprising:

capturing, using a camera of the computing device, a plurality of frames of a live scene;

generating a plurality of preview frames for an augmented scene by applying one or more augmented reality effects to the plurality of frames of the live scene, wherein each preview frame is based on a low-resolution image of the live scene, and wherein the low-resolution image has a lower resolution than a maximum resolution of the camera of the computing device;

storing at least one preview frame of the plurality of preview frames with the one or more augmented reality effects into a storage of the computing device;

displaying a live preview of the augmented scene using the plurality of preview frames;

receiving a request from a user of the computing device to capture an image of the augmented scene while the live preview is being displayed;

retrieving, in response to the request, the at least one preview frame stored in the storage of the computing device; and

outputting the retrieved at least one preview frame.

2. The method of claim 1 , wherein the low-resolution image has a smaller file size than that of a native image captured using the maximum resolution of the camera.

3. The method of claim 1 , wherein each of the plurality of frames has a resolution equal to a screen resolution of the computing device.

4. The method of claim 1 , wherein the at least one preview frame is stored in the storage of the computing device according to one or more storage rules, and wherein the one or more storage rules comprises storing a pre-determined number of frames in the storage of the computing device on a first-in-first-out basis.

5. The method of claim 1 , further comprising:

receiving a second request from the user to capture, using a native capturing mode, a second image associated with the augmented scene while the live preview is being displayed;

capturing, in response to the second request, a high-resolution image of the live scene using the camera of the computing device, wherein the high-resolution image has a higher resolution than each of the plurality of frames of the live scene;

generating a high-resolution augmented scene by applying the one or more augmented reality effects to the high-resolution image; and

outputting the high-resolution augmented scene.

6. The method of claim 1 , further comprising:

determining that a capturing mode of the computing device is a preview capturing mode.

7. The method of claim 6 , wherein the determination is based on a prediction by a machine-learning model that the preview capturing mode is a preferred capturing mode of the user.

8. The method of claim 6 , wherein the capturing mode is determined by a machine-learning model based at least on a set of user features comprising one or more of:

an age of the user;

a geographic location of the user;

a gender of the user;

a type of the computing device;

available memory of the computing device;

a network carrier;

a video content purchasing history; or

a user preference.

9. The method of claim 6 , wherein the capturing mode is determined by a machine-learning model based at least on a set of situational preferences comprising one or more of:

a bandwidth limitation;

a storage limitation;

a status associated with social network sharing;

a status associated with text messaging;

a status associated with email sending;

a network signal coverage status;

a use case;

a wireless speed; or

a user choice.

10. The method of claim 6 , wherein the capturing mode is determined by a machine-learning model based at least on a set of features associated with a recipient of the augmented scene, and wherein the set of features comprises one or more of:

a relation to the user;

a degree of separation with a social network to the user;

a preference of the recipient;

a feedback of the other users about the augmented scene; or

an interaction frequency of the recipient with the augmented scene.

11. The method of claim 6 , wherein the determination of the capturing mode is performed by the computing device.

12. The method of claim 6 , wherein the determination of the capturing mode is performed by a server associated with the computing device.

13. One or more computer-readable non-transitory storage media embodying software that is operable when executed to:

capture, using a camera of the computing device, a plurality of frames of a live scene;

generate a plurality of preview frames for an augmented scene by applying one or more augmented reality effects to the plurality of frames of the live scene, wherein each preview frame is based on a low-resolution image of the live scene, and wherein the low-resolution image has a lower resolution than a maximum resolution of the camera of the computing device;

store at least one preview frame of the plurality of preview frames with the one or more augmented reality effects into a storage of the computing device;

display a live preview of the augmented scene using the plurality of preview frames;

receive a request from a user of the computing device to capture an image of the augmented scene while the live preview is being displayed;

retrieve, in response to the request, the at least one preview frame stored in the storage of the computing device; and

output the retrieved at least one preview frame.

14. The media of claim 13 , wherein the low-resolution image has a smaller file size than that of a native image captured using the maximum resolution of the camera.

15. The media of claim 13 , wherein each of the plurality of frames has a resolution equal to a screen resolution of the computing device.

16. The media of claim 13 , wherein the at least one preview frame is stored in the storage of the computing device according to one or more storage rules, and wherein the one or more storage rules comprises storing a pre-determined number of frames in the storage of the computing device on a first-in-first-out basis.

17. The media of claim 13 , further embodying software that is operable when executed to determine that a capturing mode of the computing device is a preview capturing mode.

18. The media of claim 17 , wherein the determination is based on a prediction by a machine-learning model that the preview capturing mode is a preferred capturing mode of the user.

19. A system comprising:

one or more processors; and

a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to:

capture, using a camera of the computing device, a plurality of frames of a live scene;

generate a plurality of preview frames for an augmented scene by applying one or more augmented reality effects to the plurality of frames of the live scene, wherein each preview frame is based on a low-resolution image of the live scene, and wherein the low-resolution image has a lower resolution than a maximum resolution of the camera of the computing device;

store at least one preview frame of the plurality of preview frames with the one or more augmented reality effects into a storage of the computing device;

display a live preview of the augmented scene using the plurality of preview frames;

receive a request from a user of the computing device to capture an image of the augmented scene while the live preview is being displayed;

retrieve, in response to the request, the at least one preview frame stored in the storage of the computing device; and

output the retrieved at least one preview frame.

20. The system of claim 19 , wherein each preview frame is based on a low-resolution image of the live scene, wherein the low-resolution image has a lower resolution than a maximum resolution of the camera of the computing device, and wherein the low-resolution image has a smaller file size than a native image captured using the maximum resolution of the camera.