Abstract: A system and method are disclosed for camera calibration. In an example, a first set of candidate frames and a second set of candidate frames can be received. The first set of candidate frames can be provided based on a first video of a pattern from a first camera. The second set of candidate frames can be provided based on a second video of the pattern from a second camera. A motion of the pattern across each of the first and second set of candidate frames can be analyzed to determine a time offset. The time offset can be indicative of a difference in recording time between corresponding frames from the first and second set of candidate frames that depict the pattern at a particular location. The method can include outputting the time offset to determine camera parameters of the first and second cameras based on the time offset.

Abstract: The present disclosure relates to systems that capture a combination of image data and environmental data of the environment. The system uses the environmental data to create a detailed virtual scan of the environment. Computer generated models and images (“assets”) are inserted into the detailed virtual environment from the scan. These assets are scaled and placed within the virtual environment at specific locations and having a specific orientation. The scaled and positioned asset is then composited with the real-time video signal allowing a user to view the asset in real-time on a display.

Abstract: A system and method are disclosed for camera calibration. In an example, a first set of candidate frames and a second set of candidate frames can be received. The first set of candidate frames can be provided based on a first video of a pattern from a first camera. The second set of candidate frames can be provided based on a second video of the pattern from a second camera. A motion of the pattern across each of the first and second set of candidate frames can be analyzed to determine a time offset. The time offset can be indicative of a difference in recording time between corresponding frames from the first and second set of candidate frames that depict the pattern at a particular location. The method can include outputting the time offset to determine camera parameters of the first and second cameras based on the time offset.

Abstract: Examples are disclosed herein for segmentation and tracking of objects. A method can include receiving frames of a scene that includes an object, generating a first bounding box so that the object in a first frame of the frames is within the first bounding box, providing a first prompt based on the first bounding box, segmenting the object from the first frame based on the first prompt to provide a first mask, generating a second bounding box so that the object in a second frame of the frames is within the second bounding box based on the first mask, providing a second prompt based on the second bounding box, and segmenting the object from the second frame based on the second prompt to provide a second mask.

Abstract: This disclosure relates to digital asset animation. A method for animating a digital asset during filming of a film includes receiving first video signal data capturing a facial feature of a subject for mapping onto a digital asset, the first video signal data generated by a first device; receiving second video signal data capturing a body movement of the subject for the mapping onto the digital asset, the second video signal data generated by a second device; generating a digital asset animation of the digital asset based on the facial feature and body movement; mapping the digital asset animation onto the digital asset; and causing augmented video data to be generated in real-time during the filming of the film based on the digital asset animation of the digital asset within a virtual environment, wherein the augmented video data is provided to one or more displays for viewing.

Abstract: Systems and methods are described for digital compositing. In an example, a video frame from video frames stored in memory can be identified based on video frame latency data. The video frame latency data can specify a number of video frames to be stored in the cache memory space before the video frame is selected. A scene related information frame of the scene related information frames stored in the memory can also be identified based on a timecode of the video frame. Augmented video data that includes one or more composited video frames can be provided based on the video frame and the scene related information frame.

Abstract: Systems and methods are described for digital compositing. In an example, a video frame from video frames stored in memory can be identified based on video frame latency data. The video frame latency data can specify a number of video frames to be stored in the cache memory space before the video frame is selected. A scene related information frame of the scene related information frames stored in the memory can also be identified based on a timecode of the video frame. Augmented video data that includes one or more composited video frames can be provided based on the video frame and the scene related information frame.

Abstract: This disclosure relates to digital asset animation.

Abstract: Example systems and methods for filming are disclosed. In an example, prop spatial data for a prop device and digital asset spatial data for a virtual asset can be received. The digital asset's spatial data can be updated based on the prop data, adjusting its position, movement, and orientation in a virtual space. In some examples, a scene model, a virtual representation of a scene, can be created using depth and color data. A miniaturized diorama of the scene model can be generated. A virtual camera can be configured to provide a perspective view of the diorama, visualized on an output device. In some examples, the scene model can include virtual points corresponding to scene locations, creating a waypoint scene model. Augmented video data can incorporate these virtual points based on the waypoint scene model. The waypoint scene model can also be miniaturized to provide the diorama.

Abstract: Systems and methods are described for digital compositing. In an example, a video frame from video frames stored in memory can be identified based on video frame latency data. The video frame latency data can specify a number of video frames to be stored in the cache memory space before the video frame is selected. A scene related information frame of the scene related information frames stored in the memory can also be identified based on a timecode of the video frame. Augmented video data that includes one or more composited video frames can be provided based on the video frame and the scene related information frame.

Abstract: Systems and methods are described for digital compositing. In an example, a video frame from video frames stored in memory can be identified based on video frame latency data. The video frame latency data can specify a number of video frames to be stored in the cache memory space before the video frame is selected. A scene related information frame of the scene related information frames stored in the memory can also be identified based on a timecode of the video frame. Augmented video data that includes one or more composited video frames can be provided based on the video frame and the scene related information frame.

Abstract: This disclosure relates to digital asset animation.

Abstract: Systems and methods are described for digital compositing. In an example, a video frame from video frames stored in memory can be identified based on video frame latency data. The video frame latency data can specify a number of video frames to be stored in the cache memory space before the video frame is selected. A scene related information frame of the scene related information frames stored in the memory can also be identified based on a timecode of the video frame. Augmented video data that includes one or more composited video frames can be provided based on the video frame and the scene related information frame.

Abstract: The present disclosure relates to systems that capture a combination of image data and environmental data of the environment. The system uses the environmental data to create a detailed virtual scan of the environment. Computer generated models and images (“assets”) are inserted into the detailed virtual environment from the scan. These assets are scaled and placed within the virtual environment at specific locations and having a specific orientation. The scaled and positioned asset is then composited with the real-time video signal allowing a user to view the asset in real-time on a display.

Abstract: The present disclosure relates to systems that capture a combination of image data and environmental data of the environment. The system uses the environmental data to create a detailed virtual scan of the environment. Computer generated models and images (“assets”) are inserted into the detailed virtual environment from the scan. These assets are scaled and placed within the virtual environment at specific locations and having a specific orientation. The scaled and positioned asset is then composited with the real-time video signal allowing a user to view the asset in real-time on a display.

Abstract: The present disclosure relates to systems that capture a combination of image data and environmental data of the environment. The system uses the environmental data to create a detailed virtual scan of the environment. Computer generated models and images (“assets”) are inserted into the detailed virtual environment from the scan. These assets are scaled and placed within the virtual environment at specific locations and having a specific orientation. The scaled and positioned asset is then composited with the real-time video signal allowing a user to view the asset in real-time on a display.