Abstract: Techniques for generating aligned, augmented reality views are disclosed. In some embodiments, an estimate of a floorplan of a three-dimensional space is first generated based on one or more received views of the three-dimensional space from a camera located in the three-dimensional space. A camera pose of the camera in the three-dimensional space is next determined based on generating a corrected floorplan from the estimate of the floorplan based on foreknowledge associated with the floorplan. Display of a rendering having the determined camera pose is facilitated in an actual view of the camera, resulting in an aligned, augmented reality view.

Abstract: Techniques for generating an arbitrary view of a scene from existing images are disclosed. In some embodiments, in response to receiving a request for an image comprising a desired perspective of a scene, the image comprising the desired perspective of the scene is generated using pixels obtained from a plurality of existing images having the desired perspective, wherein one or more of the plurality of existing images are transformed to the desired perspective from other perspectives.

Abstract: Techniques for generating aligned, augmented reality views are disclosed. In some embodiments, an estimate of a floorplan of a three-dimensional space is first generated based on one or more received views of the three-dimensional space from a camera located in the three-dimensional space. A camera pose of the camera in the three-dimensional space is next determined based on generating a corrected floorplan from the estimate of the floorplan based on foreknowledge associated with the floorplan. Display of a rendering having the determined camera pose is facilitated in an actual view of the camera, resulting in an aligned, augmented reality view.

Abstract: Techniques for generating an arbitrary view of a scene from existing images of the scene are disclosed. In some embodiments, an image of a scene having a desired perspective is at least in part generated by populating some pixels of the image having the desired perspective using pixels obtained from a transformed existing image of the scene that is selected from a stored set of existing images associated with the scene and that is transformed to the desired perspective.

Abstract: A machine learning based image processing architecture and associated applications are disclosed herein. In some embodiments, a machine learning framework is trained to learn low level image attributes such as object/scene types, geometries, placements, materials and textures, camera characteristics, lighting characteristics, contrast, noise statistics, etc. Thereafter, the machine learning framework may be employed to detect such attributes in other images and process the images at the attribute level.

Abstract: A machine learning based image processing architecture and associated applications are disclosed herein. In some embodiments, a machine learning framework is trained to learn low level image attributes such as object/scene types, geometries, placements, materials and textures, camera characteristics, lighting characteristics, contrast, noise statistics, etc. Thereafter, the machine learning framework may be employed to detect such attributes in other images and process the images at the attribute level.

Abstract: A machine learning based image processing architecture and associated applications are disclosed herein. In some embodiments, a machine learning framework is trained to learn low level image attributes such as object/scene types, geometries, placements, materials and textures, camera characteristics, lighting characteristics, contrast, noise statistics, etc. Thereafter, the machine learning framework may be employed to detect such attributes in other images and process the images at the attribute level.

Abstract: Techniques associated with adaptive sampling are disclosed. In some embodiments, in response to receiving a specification of a scene to render, a sampling of each portion of the scene is determined based at least in part on the specification of the scene such that the scene is not uniformly sampled, and the scene is rendered according to the determined sampling of each portion of the scene.

Abstract: A machine learning based image processing architecture and associated applications are disclosed herein. In some embodiments, a machine learning framework is trained to learn low level image attributes such as object/scene types, geometries, placements, materials and textures, camera characteristics, lighting characteristics, contrast, noise statistics, etc. Thereafter, the machine learning framework may be employed to detect such attributes in other images and process the images at the attribute level.

Abstract: Techniques associated with adaptive sampling are disclosed. In some embodiments, in response to receiving a specification of a scene to render, a sampling of each portion of the scene is determined based at least in part on the specification of the scene such that the scene is not uniformly sampled, and the scene is rendered according to the determined sampling of each portion of the scene.

Abstract: Techniques for providing blended physical and virtual reality experiences are disclosed. In some embodiments, a rendering of an actual view of a scene as seen by a camera capturing the scene is obtained from existing assets associated with a virtualized version of the scene and displayed. The actual view of the scene comprises a known environment that includes one or more of a constrained set of objects. The rendering facilitates surfacing information associated with one or more objects comprising the actual view.

Abstract: Techniques for machine learning based image attribute determination are disclosed. In some embodiments, one or more unknown attributes of a received image comprising a prescribed environment are determined using a machine learning based framework. The machine learning based framework is at least in part trained on image data sets comprising a model environment that substantially simulates the prescribed environment.

Abstract: Techniques for generating an arbitrary view of an asset are disclosed. In some embodiments, arbitrary view generation includes storing a set of images associated with an asset in a database and generating an image comprising a requested view of the asset using at least a subset of the set of images associated with the asset that are stored in the database.

Abstract: Adaptive sampling of pixels is disclosed. In some embodiments, convergence of pixels of a rendering is evaluated by removing texture from the rendering to eliminate non-convergence due to texture complexity and determining whether pixels values satisfy convergence criteria associated with pixel sampling. Those pixels of the rendering that have not converged are sampled with one or more additional samples. The completed rendering is output. Pixels of the completed rendering satisfy the convergence criteria and are not uniformly sampled.

Abstract: Techniques for providing blended physical and virtual reality experiences are disclosed. In some embodiments, a pose of a camera of a device located in a venue is determined based at least in part on three-dimensional asset recognition in a field of view of the camera, wherein the field of view of the camera comprises an actual physical view of the venue; a virtual view corresponding to the actual view is obtained from existing assets comprising a specification of a virtualized version of the venue; and display of the virtual view is facilitated at the venue. Thus, a virtual reality of a physical space is provided while at the physical space based on actual three-dimensional objects detected or recognized in the physical space.

Abstract: Improved techniques for generating video content are disclosed. In some embodiments, a frame is rendered using a first rendering option. It is then determined whether the frame is an independent frame (I-frame) or a predictive frame (P-frame). In the event that the frame is an I-frame, the frame is rendered using a second rendering option that has a higher computational complexity than the first rendering option and encoded independently. In the event that the frame is a P-frame, motion vectors and prediction error with respect to the frame and one or more other frames are determined and encoded.

Abstract: Adaptive sampling of pixels is disclosed. In some embodiments, a rendering of a scene is generated by sampling each pixel of the rendering with a prescribed number of samples. Subsequently, those pixels of the rendering that do not satisfy a noise threshold are iteratively sampled with an additional sample during each iteration until all pixels of the rendering satisfy the noise threshold. The noise threshold is associated with noise arising due to under sampling. Pixels comprising the completed rendering are not uniformly sampled.

Abstract: Techniques for generating an arbitrary view of a scene are disclosed. In some embodiments, arbitrary view generation includes storing sets of images associated with corresponding assets in a database and generating an image comprising a requested view of a scene using images associated with one or more assets comprising the scene that are stored in the database.

Abstract: Techniques for generating an arbitrary view of an asset are disclosed. In some embodiments, arbitrary view generation includes storing a set of images associated with an asset in a database and generating an image comprising a requested view of the asset using at least a subset of the set of images associated with the asset that are stored in the database.

Abstract: Techniques for generating an arbitrary view of an asset are disclosed. In some embodiments, arbitrary view generation includes storing a set of images of an asset, wherein each image comprising at least a subset of the set of images is rendered from a three-dimensional model of the asset, and generating an image comprising an arbitrary perspective of the asset at least in part by populating the image comprising the arbitrary perspective with pixels harvested from one or more images comprising the set of images.