System for image compositing including training with custom synthetic data
Embodiments allow live action images from an image capture device to be composited with computer generated images in real-time or near real-time. The two types of images (live action and computer generated) are composited accurately by using a depth map. In an embodiment, the depth map includes a “depth value” for each pixel in the live action image. In an embodiment, steps of one or more of feature extraction, matching, filtering or refinement can be implemented, at least in part, with an artificial intelligence (AI) computing approach using a deep neural network with training. A combination of computer-generated (“synthetic”) and live-action (“recorded”) training data is created and used to train the network so that it can improve the accuracy or usefulness of a depth map so that compositing can be improved.
1. A method for compositing image elements, the method comprising:
(a) during preparation:
obtaining custom recorded data of an aspect of an environment to be used during a live action capturing event;
modifying the aspect in a computer program to create a rendering of a modified environment;
generating custom synthetic data from the modified environment;
selecting a deep neural network and training the selected deep neural network using a dataset derived, at least in part, from the custom synthetic data;
(b) during the live action capturing event:
using the selected deep neural network to process image information from one or more auxiliary cameras to generate a depth map of the environment;
correlating the depth map with at least a portion of picture elements in at least one picture image of the environment obtained from an image capture device; and
using the correlated depth map to composite one or more digital elements with one or more picture elements.
2. The method of claim 1 , further comprising:
re-projecting a disparity map into an image from the image capture device; and
infilling holes in the re-projected disparity map.
3. The method of claim 1 , further comprising:
a signal interface for receiving image camera information and providing the image camera information to one or more processors for processing by the selected deep neural network.
4. The method of claim 3 , wherein the image camera information includes a focal length of an image camera.
5. An apparatus for compositing image elements, the apparatus comprising:
one or more digital processors;
a tangible, non-transitory processor-readable medium including instructions for:
(a) during preparation:
obtaining custom recorded data of an aspect of an environment to be used during a live action capturing event;
modifying the aspect in a computer program to create a rendering of a modified environment;
generating custom synthetic data from the modified environment;
selecting a deep neural network and training the selected deep neural network using a dataset derived, at least in part, from the custom synthetic data;
(b) during the live action capturing event:
using the selected deep neural network to process image information from one or more auxiliary cameras to generate a depth map of the environment;
correlating the depth map with at least a portion of picture elements in at least one picture image of the environment obtained from an image capture device; and
using the correlated depth map to composite one or more digital elements with one or more picture elements.
6. The apparatus of claim 5 , further comprising:
re-projecting a disparity map into an image from the image capture device; and
infilling holes in the re-projected disparity map.
7. The apparatus of claim 5 , further comprising:
a signal interface for receiving image camera information and providing the image camera information to one or more processors for processing by the selected deep neural network.
8. The apparatus of claim 7 , wherein the image camera information includes a focal length of an image camera.
9. A tangible, non-transitory processor-readable medium including instructions executable by one or more digital processors for compositing image elements, the processor-readable medium comprising one or more instructions for:
(a) during preparation:
receiving custom recorded data of an aspect of an environment to be used during a live action capturing event;
modifying the aspect in a computer program to create a rendering of a modified environment;
generating custom synthetic data from the modified environment; and
creating a training dataset derived, at least in part, from the custom synthetic data, wherein the training dataset is suitable for training a deep neural network to process image information from one or more auxiliary cameras to generate a depth map of the environment.
10. The tangible, non-transitory processor-readable medium of claim 9 , further comprising:
re-projecting a disparity map into an image from the image capture device.
11. The tangible, non-transitory processor-readable medium of claim 10 , further comprising:
infilling holes in the re-projected disparity map.
12. The tangible, non-transitory processor-readable medium of claim 9 , further comprising:
a signal interface for receiving image camera information and providing the image camera information to one or more processors for processing by the selected deep neural network.
13. The tangible, non-transitory processor-readable medium of claim 12 , wherein the image camera information includes a focal length of an image camera.
14. The tangible, non-transitory processor-readable medium of claim 9 , wherein an aspect includes at least a portion of a movie set.
15. The tangible, non-transitory processor-readable medium of claim 9 , wherein an aspect includes at least a portion of a costume.
16. The tangible, non-transitory processor-readable medium of claim 9 , wherein an aspect includes at least a portion of an actor.
17. The tangible, non-transitory processor-readable medium of claim 9 , wherein an aspect includes lighting.
18. The tangible, non-transitory processor-readable medium of claim 9 , wherein an aspect includes an object's position.
19. The tangible, non-transitory processor-readable medium of claim 18 , wherein the object includes a camera.
20. The tangible, non-transitory processor-readable medium of claim 9 , wherein an aspect includes a camera setting.