Abstract: According to embodiments herein, a device obtains visualization data that depicts at least one three-dimensional object. The device sanitizes the visualization data, in part by: identifying neighboring polygons of the at least one three-dimensional object and their windings, and correcting errors in the neighboring polygons and their windings. The device also decimates meshes of polygons in the sanitized visualization data, to form compressed visualization data, by: performing one or more sanity checks, prior to performing an atomic decimation operation or texture compression; and storing, by the device, the compressed visualization data in one or more files.

Abstract: In one embodiment, a device obtains visualization data that depicts a three-dimensional item. The device identifies, from the visualization data, one or more materials of the three-dimensional item. The device generates, based on the visualization data, physically based rendering data for the one or more materials of the three-dimensional item. The device forms a container that includes the visualization data and the physically based rendering data. The visualization data is stored using a file format that does not support the physically based rendering data.

Abstract: According to embodiments herein, a device obtains visualization data that depicts at least one three-dimensional object. The device sanitizes the visualization data, in part by: identifying neighboring polygons of the at least one three-dimensional object and their windings, and correcting errors in the neighboring polygons and their windings. The device also decimates meshes of polygons in the sanitized visualization data, to form compressed visualization data, by: performing one or more sanity checks, prior to performing an atomic decimation operation or texture compression; and storing, by the device, the compressed visualization data in one or more files.

Abstract: In one embodiment, a device obtains visualization data that depicts a three-dimensional item. The device identifies, from the visualization data, one or more materials of the three-dimensional item. The device generates, based on the visualization data, physically based rendering data for the one or more materials of the three-dimensional item. The device forms a container that includes the visualization data and the physically based rendering data. The visualization data is stored using a file format that does not support the physically based rendering data.

Abstract: In one embodiment, a device obtains visualization data that depicts a three-dimensional item. The device identifies, from the visualization data, one or more materials of the three-dimensional item. The device generates, based on the visualization data, physically based rendering data for the one or more materials of the three-dimensional item. The device forms a container that includes the visualization data and the physically based rendering data. The visualization data is stored using a file format that does not support the physically based rendering data.

Abstract: According to embodiments herein, a device obtains visualization data that depicts at least one three-dimensional object. The device sanitizes the visualization data, in part by: identifying neighboring polygons of the at least one three-dimensional object and their windings, and correcting errors in the neighboring polygons and their windings. The device also decimates meshes of polygons in the sanitized visualization data, to form compressed visualization data, by: performing one or more sanity checks, prior to performing an atomic decimation operation or texture compression; and storing, by the device, the compressed visualization data in one or more files.

Abstract: Various techniques are described herein that provide for a real-time image or video processing system that is able to capture and stream or record/store video content of an object, and turn the captured content into a new video format that can be properly projected onto a pyramid holographic projector. In one specific embodiment, the techniques herein capture a video selfie of a user and stream it live or else store it for playback later as a saved message. Other embodiments, such as controlled avatars, animated characters, etc., may also be converted from a standard 2D format into a pyramid hologram format, either in real-time or else during post-processing, accordingly.

Abstract: Various techniques are described herein that provide for real-time quality control during manufacturing using augmented reality. In particular, in one embodiment, techniques herein project a three-dimensional (3D) virtual shape/model onto a work-in-progress part in the real-world in order to see defects in real-time, thus allowing for mid-manufacturing corrections. The embodiments herein generally consist of first calibrating a “virtual world” to the real world, then calibrating the physical product to the virtual world, and lastly projecting information onto the physical product, such as various design information and/or quality control information.

Abstract: Various techniques are described herein that provide for real-time quality control during manufacturing using augmented reality. In particular, in one embodiment, techniques herein project a three-dimensional (3D) virtual shape/model onto a work-in-progress part in the real-world in order to see defects in real-time, thus allowing for mid-manufacturing corrections. The embodiments herein generally consist of first calibrating a “virtual world” to the real world, then calibrating the physical product to the virtual world, and lastly projecting information onto the physical product, such as various design information and/or quality control information.

Abstract: Various techniques are described herein that provide for a real-time image or video processing system that is able to capture and stream or record/store video content of an object, and turn the captured content into a new video format that can be properly projected onto a pyramid holographic projector. In one specific embodiment, the techniques herein capture a video selfie of a user and stream it live or else store it for playback later as a saved message. Other embodiments, such as controlled avatars, animated characters, etc., may also be converted from a standard 2D format into a pyramid hologram format, either in real-time or else during post-processing, accordingly.

Abstract: Systems and methods herein are directed to an artificial intelligence (AI) character capable of natural verbal and visual interactions with a human. In one embodiment, an AI character system receives, in real-time, one or both of an audio user input and a visual user input of a user interacting with the AI character system. The AI character systems determines one or more avatar characteristics based on the one or both of the audio user input and the visual user input of the user. The AI character system manages interaction of an avatar with the user based on the one or more avatar characteristics.