Photoreal character configurations for spatial computing
Systems and methods for displaying a virtual character in a mixed reality environment are disclosed. In some embodiments, a view of the virtual character is based on an animation rig comprising primary joints and helper joints. The animation rig may be in a pose defined by spatial relationships between the primary joints and helper joints. The virtual character may be moving in the mixed reality environment. In some instances, the virtual character may be moving based on a comparison of interestingness values associated with elements in the mixed reality environment. The spatial relationship transformation associated with the movement may be indicated by movement information. In some embodiments, the movement information is received from a neural network.
1. A method comprising:
displaying, on a display of a wearable head device, a view of a character in a mixed reality environment, wherein:
the view of the character is based on an animation rig associated with the character;
the animation rig comprises a primary joint and a helper joint,
the primary joint is associated with skeletal joints of the character, and
said displaying comprises displaying the animation rig in a first pose comprising a first spatial relationship between the primary joint and the helper joint;
determining that the animation rig is transitioning from the first pose to a second pose, wherein the second pose comprises a second spatial relationship between the primary joint and the helper joint; and
updating a display, on the display of the wearable head device, of the animation rig from the first pose to the second pose based on movement information, wherein:
the movement information indicates a transformation from the first spatial relationship to the second spatial relationship, and
the movement information comprises a quaternion component value and an output of a loss function, the loss function comprising a combination of a mean squared error loss of the quaternion component value and further comprising a penalty for the component value.
2. The method of claim 1 , wherein the character is positioned on a surface of the mixed reality environment, the method further comprising:
detecting, with a sensor of the wearable head device, the surface of the mixed reality environment; and
determining an alignment of the animation rig and the surface based on the detected surface, wherein one or more of the first pose and the second pose are determined based on the alignment of the animation rig and the surface.
3. The method of claim 1 , further comprising:
determining that the animation rig is transitioning from the second pose to a third pose, wherein the third pose comprises a third spatial relationship between a second primary joint and a second helper joint; and
updating a display, on the display of the wearable head device, of the animation rig from the second pose to the third pose based on second movement information, wherein:
the second movement information indicates a transformation from the second spatial relationships to the third spatial relationships, and
the second movement information comprises a second quaternion component value and an output of a second loss function, the second loss function comprising combination of a second mean squared error loss of the second quaternion component value and further comprising a second penalty for the second component value.
4. The method of claim 3 , wherein the first loss function comprises the second loss function.
5. The method of claim 1 , further comprising:
displaying, on the display of the wearable head device, a view of a second character in the mixed reality environment, wherein:
the view of the second character is based on a second animation rig associated with the second character;
the second animation rig comprises a second primary joint and a second helper joint,
the second primary joint is associated with skeletal joints of the second character, and
said displaying of the view of the second character comprises displaying the second animation rig in a third pose comprising a third spatial relationship between the second primary joint and the second helper joint;
determining that the second animation rig is transitioning from the third pose to a fourth pose, wherein the fourth pose comprises a fourth spatial relationship between the second primary joint and the second helper joint; and
updating a display, on the display of the wearable head device, of the second animation rig from the third pose to the fourth pose based on second movement information, wherein the second movement information indicates a transformation from the third spatial relationship to the fourth spatial relationship.
6. The method of claim 1 , wherein:
the first pose corresponds to a first gaze position, and
the second pose corresponds to a second gaze position.
7. The method of claim 1 , wherein:
the first pose corresponds to a first gesture, and
the second pose corresponds to a second gesture.
8. The method of claim 1 , wherein:
the first pose corresponds to a first eye position, and
the second pose corresponds to a second eye position.
9. The method of claim 1 , wherein said determining that the animation rig is moving from the first pose to the second pose comprises determining the animation rig is in the first pose longer than a threshold time.
10. The method of claim 9 , wherein the threshold time is determined based on an application associated with the character.
11. The method of claim 9 , wherein the threshold time is determined based on a state of the character at a time between the first time and the second time.
12. The method of claim 9 , wherein the threshold time is determined based on a property of an element in the character's line of sight.
13. The method of claim 9 , wherein the threshold time is determined based on a state of a user of the wearable head device.
14. The method of claim 1 , further comprising presenting animation rig data as input to a neural network, wherein the movement information is determined based on an output of the neural network.
15. The method of claim 1 , wherein the movement information is determined further based on training data presented to a neural network.
16. The method of claim 1 , further comprising presenting a result of the loss function as input to a neural network, wherein the movement information is determined based on an output of the neural network.
17. The method of claim 1 , wherein the movement information comprises parameterized rotations.
18. A system comprising:
a wearable head device comprising a display; and
one or more processors configured to execute a method comprising:
displaying, on the display of a wearable head device, a view of a character in a mixed reality environment, wherein:
the view of the character is based on an animation rig associated with the character;
the animation rig comprises a primary joint and a helper joint,
the primary joint is associated with skeletal joints of the character, and
said displaying comprises displaying the animation rig in a first pose comprising a first spatial relationship between the primary joint and the helper joint;
determining that the animation rig is transitioning from the first pose to a second pose, wherein the second pose comprises a second spatial relationship between the primary joint and the helper joint; and
updating a display, on the display of the wearable head device, of the animation rig from the first pose to the second pose based on movement information, wherein:
the movement information indicates a transformation from the first spatial relationship to the second spatial relationship, and
the movement information comprises a quaternion component value and an output of a loss function, the loss function comprising a combination of a mean squared error loss of the quaternion component value and further comprising a penalty for the component value.
19. The system of claim 18 , wherein the method further comprises presenting animation rig data as input to a neural network, wherein the movement information is determined based on an output of the neural network.
20. A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to execute a method comprising:
displaying, on a display of a wearable head device, a view of a character in a mixed reality environment, wherein:
the view of the character is based on an animation rig associated with the character;
the animation rig comprises a primary joint and a helper joint,
the primary joint is associated with skeletal joints of the character, and
said displaying comprises displaying the animation rig in a first pose comprising a first spatial relationship between the primary joint and the helper joint;
determining that the animation rig is transitioning from the first pose to a second pose, wherein the second pose comprises a second spatial relationship between the primary joint and the helper joint; and
updating a display, on the display of the wearable head device, of the animation rig from the first pose to the second pose based on movement information, wherein:
the movement information indicates a transformation from the first spatial relationship to the second spatial relationship, and
the movement information comprises a quaternion component value and an output of a loss function, the loss function comprising a combination of a mean squared error loss of the quaternion component value and further comprising a penalty for the component value.