IP Library Granted Patent US 10,242,474
Granted Patent B2
US 10,242,474 · App. 14/800,640 · Granted Mar 26, 2019

Artificially rendering images using viewpoint interpolation and extrapolation

Inventors: Stefan Johannes Josef Holzer (San Mateo, CA); Stephen David Miller (San Francisco, CA); Martin Saelzle (San Francisco, CA); Radu Bogdan Rusu (San Francisco, CA)
Assignee: Fyusion, Inc.
G06T11/60G06T15/205G06T2210/44
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,242,474
App. No.
14/800,640
Granted
Mar 26, 2019
Kind
B2
Abstract

Various embodiments of the present invention relate generally to mechanisms and processes relating to artificially rendering images using viewpoint interpolation and extrapolation. According to particular embodiments, a method includes applying a transform to estimate a path outside the trajectory between a first frame and a second frame, where the first frame includes a first image captured from a first location and the second frame includes a second image captured from a second location. The process also includes generating an artificially rendered image corresponding to a third location positioned on the path. The artificially rendered image is generated by interpolating a transformation from the first location to the third location and from the third location to the second location, gathering image information from the first frame and the second frame by transferring first image information from the first frame to the third frame and second image information from the second frame to the third frame, and combining the first image information and the second image information.

Claims (32)

1. A method comprising:

moving a mobile device with a camera through space in a locally convex or locally concave motion;

obtaining, from the camera throughout the movement of the mobile device, a plurality of frames having location information, wherein the plurality of frames include a first frame and a second frame;

applying a transform to estimate a path outside the trajectory between the first frame and the second frame, wherein the first frame includes a first image captured by the camera from a first location and the second frame includes a second image captured by the camera from a second location;

generating an artificially rendered image corresponding to a third location, wherein the third location is positioned on the path, the artificially rendered image generated by:

interpolating a transformation from the first location to the third location and from the third location to the second location;

gathering image information from the first frame and the second frame by transferring first image information from the first frame to the third frame based on the interpolated transformation and second image information from the second frame to the third frame based on the interpolated transformation; and

combining the first image information and the second image information;

determining whether an occlusion is present due to movement of multiple layers; and

if an occlusion is detected, determining whether the layer closer to the camera is non-see-through or partially see-through, wherein if the layer closer to the camera is non-see-through, only image information from the layer closer to the camera is taken, wherein if the layer closer to the camera is partially see-through, then image information is taken from both layers,

wherein generating the artificially rendered image includes filling in missing information using viewpoint extrapolation by moving different layers of the multiple layers in a motion perpendicular to the trajectory.

2. The method of claim 1 , wherein the transform warps the first image and second image according to curvature and direction of the estimated path.

3. The method of claim 1 , wherein the transform implements homography.

4. The method of claim 1 , wherein the transform implements spherical projection.

5. The method of claim 1 , wherein the transform implements cylindrical projection.

6. The method of claim 1 , wherein the first image is associated with a first layer and wherein the second image is associated with the first layer.

7. A non-transitory computer readable medium comprising:

computer code moving a mobile device with a camera through space in a locally convex or locally concave motion;

computer code for obtaining, from the camera throughout the movement of the mobile device, a plurality of frames having location information, wherein the plurality of frames include a first frame and a second frame;

computer code for applying a transform to estimate a path outside the trajectory between the first frame and the second frame, wherein the first frame includes a first image captured by the camera from a first location and the second frame includes a second image captured by the camera from a second location computer code for applying a transform to estimate a path outside the trajectory between a first frame and a second frame, wherein the first frame includes a first image captured from a first location and the second frame includes a second image captured from a second location;

computer code for generating an artificially rendered image corresponding to a third location, wherein the third location is positioned on the path, the artificially rendered image generated by:

interpolating a transformation from the first location to the third location and from the third location to the second location;

gathering image information from the first frame and the second frame by transferring first image information from the first frame to the third frame based on the interpolated transformation and second image information from the second frame to the third frame based on the interpolated transformation; and

combining the first image information and the second image information;

computer code for determining whether an occlusion is present due to movement of multiple layers; and

computer code for determining, if an occlusion is detected, whether the layer closer to the camera is non-see-through or partially see-through, wherein if the layer closer to the camera is non-see-through, only image information from the layer closer to the camera is taken, wherein if the layer closer to the camera is partially see-through, then image information is taken from both layers,

wherein generating the artificially rendered image includes filling in missing information using viewpoint extrapolation by moving different layers of the multiple layers in a motion perpendicular to the trajectory.

8. The non-transitory computer readable medium of claim 7 , wherein the transform warps the first image and second image according to curvature and direction of the estimated path.

9. The non-transitory computer readable medium of claim 7 , wherein the transform implements homography.

10. The non-transitory computer readable medium of claim 7 , wherein the transform implements spherical projection.

11. The non-transitory computer readable medium of claim 7 , wherein the transform implements cylindrical projection.

12. The non-transitory computer readable medium of claim 7 , wherein the first image is associated with a first layer and wherein the second image is associated with the first layer.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 12, 2016
From: HOLZER, STEFAN JOHANNES JOSEF; MILLER, STEPHEN DAVID; SAELZLE, MARTIN; RUSU, RADU BOGDAN
To: FYUSION, INC.
Reel/Frame 037721/0037 →
Continuity (1)
Related Publication 20170018054A1 · Jan 19, 2017
Cited By (10)
US 12,190,916 US 12,261,990 US 12,380,634 US 12,381,995 US 12,432,327 US 12,495,134 US 12,525,045 US 12,541,933 US 12,657,238 US 12,665,986