Virtual video projection system to synch animation sequences
A method of synchronizing an animation sequence with a video includes placing a virtual camera in a 3D model of a site captured in the video at the same location and the same orientation as those of a video camera that captured the video, generating a set of virtual frames of the animation sequence by projecting the 3D model onto a scene frame from a viewpoint of the virtual camera, for each of a plurality of virtual key frames, placing a virtual object corresponding to a moving object captured in the video in the 3D model at a respective location that matches with the respective position of the moving object in a corresponding key frame of the video, and playing the set of virtual frames by stepping through time such that the plurality of virtual key frames is in synch with the plurality of key frames of the video.
1. A method of synchronizing an animation sequence with a video footage, the method comprising:
obtaining a digital three-dimensional (3D) model of a site captured in the video footage by a video camera installed in the site, the video camera having a set of camera parameters;
identifying a plurality of key frames of the video footage, wherein a moving object is at a respective position in a respective key frame of the plurality of key frames;
placing a first virtual camera in the digital 3D model at a first location and a first orientation corresponding to a location and an orientation of the video camera in the site, the first virtual camera having a first set of virtual camera parameters, at least some virtual camera parameters of the first set of virtual camera parameters are same as some corresponding camera parameters of the set of camera parameters of the video camera;
generating a first set of virtual frames of the animation sequence by projecting the digital 3D model onto a first scene frame from a viewpoint of the first virtual camera using the first set of virtual camera parameters, the first set of virtual frames including a first plurality of virtual key frames, each virtual key frame corresponding to a respective key frame in the video footage;
rendering at least a subset of a set of pixels of the video footage in each virtual frame of the first set of virtual frames;
for each respective virtual key frame, placing a virtual object corresponding to the moving object at a respective location in the digital 3D model that matches with the respective position of the moving object in a corresponding key frame; and
playing the first set of virtual frames of the animation sequence while the video footage is overlaid on the subset of the set of pixels, wherein the animation sequence and the video footage are played simultaneously by stepping through time such that the first plurality of virtual key frames is in synch with the plurality of key frames of the video footage.
2. The method of claim 1 further comprising creating a virtual wall in the digital 3D model, and wherein the subset of the set of pixels of the video footage are rendered on the virtual wall.
3. The method of claim 1 wherein the first set of virtual camera parameters of the first virtual camera comprises a focal length and a field of view.
4. The method of claim 3 wherein the first set of virtual camera parameters of the first virtual camera further comprises calibration parameters.
5. The method of claim 1 wherein the digital 3D model of the site comprises a point cloud generated by scanning the site using a 3D scanner.
6. The method of claim 1 wherein the digital 3D model of the site is generated using computer graphics.
7. The method of claim 1 further comprising:
placing a second virtual camera in the digital 3D model at a second location and a second orientation different from the first location and the first orientation, respectively;
generating a second set of virtual frames of the animation sequence by projecting the digital 3D model onto a second scene frame from a viewpoint of the second virtual camera, the second set of virtual frames including a second plurality of virtual key frames corresponding to the plurality of key frames in the video footage; and
playing the second set of virtual frames of the animation sequence by stepping through time such that the second plurality of virtual key frames is in synch with the plurality of key frames of the video footage.
8. The method of claim 7 wherein the second virtual camera has a second set of virtual camera parameters different from the first set of virtual camera parameters.
9. The method of claim 1 wherein the moving object has a respective pose in a respective key frame of the plurality of key frames, and the method further comprising, for each respective virtual key frame, posing the virtual object to match the respective pose of the moving object in a corresponding key frame.
10. A system for synchronizing an animation sequence with a video footage, the system comprising:
a memory for storing a digital three-dimensional (3D) model of a site captured in the video footage by a video camera installed in the site, the video footage including a plurality of key frames, wherein a moving object is at a respective position in a respective key frame of the plurality of key frames, and the video camera having a set of camera parameters;
a projection module configured to place a first virtual camera in the digital 3D model at a first location and a first orientation corresponding to a location and an orientation of the video camera in the site, the first virtual camera having a first set of virtual camera parameters, at least some virtual camera parameters of the first set of virtual camera parameters are same as some corresponding camera parameters of the set of camera parameters of the video camera;
a processor configured to generate a first set of virtual frames of the animation sequence by projecting the digital 3D model onto a first scene frame from a viewpoint of the first virtual camera using the first set of virtual camera parameters, the first set of virtual frames including a first plurality of virtual key frames, each virtual key frame corresponding to a respective key frame in the video footage;
a graphics shader configured to render at least a subset of a set of pixels of the video footage in each virtual frame of the first set of virtual frames;
an interpolator configured to, for each respective virtual key frame, place a virtual object corresponding to the moving object at a respective location in the digital 3D model that matches with the respective position of the moving object in a corresponding key frame; and
a key-frame timer for synchronizing playing of the first set of virtual frames of the animation sequence while the video footage is overlaid on the subset of the set of pixels such that the first plurality of virtual key frames is in synch with the plurality of key frames of the video footage.
11. The system of claim 10 wherein the processor is further configured to create a virtual wall in the digital 3D model, and wherein the subset of the set of pixels of the video footage are rendered on the virtual wall.
12. The system of claim 10 further comprising a display configured to play the first set of virtual frames of the animation sequence using the key-frame timer.
13. The system of claim 10 wherein the first set of virtual camera parameters of the first virtual camera comprises a focal length and a field of view.
14. The system of claim 13 wherein the first set of virtual camera parameters of the first virtual camera further comprises calibration parameters.
15. The system of claim 10 wherein the digital 3D model of the site comprises a point cloud generated by scanning the site using a 3D scanner.
16. The system of claim 10 wherein the digital 3D model of the site is generated using computer graphics.
17. The system of claim 10 wherein:
the projection module is further configured to place a second virtual camera in the digital 3D model at a second location and a second orientation different from the first location and the first orientation, respectively; and
the processor is further configured to generate a second set of virtual frames of the animation sequence by projecting the digital 3D model onto a second scene frame from a viewpoint of the second virtual camera.
18. The system of claim 10 wherein the moving object has a respective pose in a respective key frame of the plurality of key frames, and the interpolator is further configured to, for each respective virtual key frame, posing the virtual object to match the respective pose of the moving object in a corresponding key frame.