Abstract: Example image processing systems and methods are described. In one implementation, a recording device captures images and measurements from an inertial measurement unit (IMU). A rendering system generates encoded video data based on the captured images and measurements from the IMU, where the encoded video data includes at least one region that stores supplemental data. The encoded video data is then rendered for viewing by a user proximate a display device.

Abstract: A text-to-image prompt is processed using a text-to-image machine learning model to obtain a non-immersive (e.g., rectilinear image). The non-immersive image may be enhanced by a superresolution machine learning model and processed with a monoscopic depth estimation model to obtain a depthmap. The non-immersive image and the depthmap may be converted to an immersive projection (e.g., F-theta) and corresponding depth map. The immersive projection may be out-painted. The immersive projection may be used to generate video with simulated camera movement, output on a VR headset, and/or processed to remove a background layer and displayed on an AR headset, or on an holographic glasses-free three-dimensional display.

Abstract: Example image processing systems and methods are described. In one implementation, a web browser executes a program configured to render video in the web browser. The image processing system identifies multiple shaders associated with the program and instructs a graphics processing unit (GPU) how to render video in the web browser based on the multiple shaders. The program accesses video data and metadata associated with the video to be rendered and communicates video data associated with the video to be rendered to the GPU for viewing by a user proximate a display device coupled to the GPU.

Abstract: Example image processing systems and methods are described. In one implementation, a recording device captures images and measurements from an inertial measurement unit (IMU). A rendering system generates encoded video data based on the captured images and measurements from the IMU, where the encoded video data includes at least one region that stores supplemental data. The encoded video data is then rendered for viewing by a user proximate a display device.

Abstract: Example video processing systems and methods are described. In one implementation, compressed video data is received from a recording device. Additionally, metadata associated with the compressed video data is received such that the metadata includes frame-specific metadata associated with frames in the compressed video data. Further, an application program is received and configured to generate a real-time interactive experience for a user based on the compressed video data and the metadata associated with the compressed video data. A non-fungible token (NFT) is generated that includes the compressed video data, the metadata associated with the compressed video data, and the application program.

Abstract: Example virtual reality systems and methods are described. In one implementation, a camera captures 6DOF (6 Degrees of Freedom) 3D (Three-Dimensional) videos while the camera is in motion. A rendering system renders the 6DOF 3D videos while minimizing vestibulo-ocular conflict. A virtual reality system presents the rendered 6DOF 3D videos to a user of the virtual reality system.