Object tracking using sparse sensor captures

1. A method comprising, by one or more computing systems:

instructing, at a first time, a camera having a plurality of pixel sensors to use the plurality of pixel sensors to capture a first image of an environment comprising an object;

predicting, using at least the first image, a projection of the object appearing in a virtual image plane associated with a predicted camera pose at a second time;

determining, based on the predicted projection of the object, a first region of pixels and a second region of pixels;

generating pixel-activation instructions for the first region of pixels and the second region of pixels;

instructing the camera to capture a second image of the environment at the second time according to the pixel-activation instructions, wherein the pixel-activation instructions are configured to cause a first subset of the plurality of pixel sensors to sample the first region of pixels and a second subset of the plurality of pixel sensors to sample the second region of pixels, wherein the first subset of the plurality of pixel sensors used for sampling the first region of pixels is more dense than the second subset of the plurality of pixel sensors used for sampling the second region of pixels; and

tracking, based on the second image, the object at the second time.

2. The method of claim 1 , wherein the subset of the plurality of pixel sensors are activated and a second subset of the plurality of pixel sensors are inactivated at the second time to capture the second image.

3. The method of claim 1 , further comprising:

identifying an object type of the object based on the first image;

accessing a prediction model associated with the object type; and

using the prediction model to determine the predicted object pose of the object at the second time.

4. The method of claim 1 , further comprising:

generating an artificial-reality effect based on a second object pose of the object, wherein the second object pose is determined based on the second image; and

displaying the artificial-reality effect using a head-mounted device worn by a user;

wherein the camera is attached to the head-mounted device worn by the user.

5. The method of claim 1 , wherein the pixel-activation instructions are further generated based on a buffer region around the first region of pixels and the second region of pixels.

6. The method of claim 5 , wherein the size of the buffer region is proportional to the time between the first time and the second time.

7. The method of claim 5 , wherein the size of the buffer region is proportional to a framerate of the camera.

8. The method of claim 5 , further comprising:

activating all the pixels within the buffer region.

9. The method of claim 5 , further comprising:

activating a sparse sample of pixels within the buffer region.

10. The method of claim 9 , further comprising:

increasing the sampling of pixels within the first region of pixels and the second region of pixels.

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

instruct, at a first time, a camera having a plurality of pixel sensors to use the plurality of pixel sensors to capture a first image of an environment comprising an object;

predict, using at least the first image, a projection of the object appearing in a virtual image plane associated with a predicted camera pose at a second time;

determine, based on the predicted projection of the object, a first region of pixels and a second region of pixels;

generate pixel-activation instructions for the first region of pixels and the second region of pixels;

instruct the camera to capture a second image of the environment at the second time according to the pixel-activation instructions, wherein the pixel-activation instructions are configured to cause a first subset of the plurality of pixel sensors to sample the first region of pixels and a second subset of the plurality of pixel sensors to sample the second region of pixels, wherein the first subset of the plurality of pixel sensors used for sampling the first region of pixels is more dense than the second subset of the plurality of pixel sensors used for sampling the second region of pixels; and

track, based on the second image, the object at the second time.

12. The media of claim 11 , wherein the subset of the plurality of pixel sensors are activated and a second subset of the plurality of pixel sensors are inactivated at the second time to capture the second image.

13. The media of claim 11 , wherein the software is further operable when executed to:

identify an object type of the object based on the first image;

access a prediction model associated with the object type; and

use the prediction model to determine the predicted object pose of the object at the second time.

14. The media of claim 11 , wherein the software is further operable when executed to:

generate an artificial-reality effect based on a second object pose of the object, wherein the second object pose is determined based on the second image; and

display the artificial-reality effect using a head-mounted device worn by a user;

wherein the camera is attached to the head-mounted device worn by the user.

15. The media of claim 11 , wherein the pixel-activation instructions are further generated based on a buffer region around the first region of pixels and the second region of pixels.

16. 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:

instruct, at a first time, a camera having a plurality of pixel sensors to use the plurality of pixel sensors to capture a first image of an environment comprising an object;

predict, using at least the first image, a projection of the object appearing in a virtual image plane associated with a predicted camera pose at a second time;

determine, based on the predicted projection of the object, a first region of pixels and a second region of pixels;

generate pixel-activation instructions for the first region of pixels and the second region of pixels;

instruct the camera to capture a second image of the environment at the second time according to the pixel-activation instructions, wherein the pixel-activation instructions are configured to cause a first subset of the plurality of pixel sensors to sample the first region of pixels and a second subset of the plurality of pixel sensors to sample the second region of pixels, wherein the first subset of the plurality of pixel sensors used for sampling the first region of pixels is more dense than the second subset of the plurality of pixel sensors used for sampling the second region of pixels; and

track, based on the second image, the object at the second time.

17. The system of claim 16 , wherein the subset of the plurality of pixel sensors are activated and a second subset of the plurality of pixel sensors are inactivated at the second time to capture the second image.

18. The system of claim 16 , wherein the processors are further operable when executing the instructions to:

identify an object type of the object based on the first image;

access a prediction model associated with the object type; and

use the prediction model to determine the predicted object pose of the object at the second time.

19. The system of claim 16 , wherein the processors are further operable when executing the instructions to:

generate an artificial-reality effect based on a second object pose of the object, wherein the second object pose is determined based on the second image; and

display the artificial-reality effect using a head-mounted device worn by a user;

wherein the camera is attached to the head-mounted device worn by the user.

20. The system of claim 16 , wherein the pixel-activation instructions are further generated based on a buffer region around the first region of pixels and the second region of pixels.