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 for generating an arbitrary ensemble view from existing views of a plurality of scenes are disclosed. In some embodiments, for each of a plurality of scenes, each of a corresponding set of one or more views is normalized to a desired perspective if its existing perspective is different than the desired perspective. An ensemble view comprising the plurality of scenes that has the desired perspective is generated at least in part using pixels from views of the scenes having the desired perspective including the normalized views.

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: 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 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 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: Improved techniques for generating video content are disclosed. In some embodiments, a frame is first 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. In the event that the frame is a P-frame, the frame as rendered by the first rendering option and a previous frame as rendered by the first rendering option are used to determine prediction error. The first rendering option comprises a lower computational complexity than the second rendering option.

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: 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 views of the three-dimensional space from a camera of a device located in the three-dimensional space. A cost function is next minimized with respect to the estimate of the floorplan to generate a corrected floorplan having less error than the estimated floorplan, and a camera pose corresponding to the corrected floorplan is determined. 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 are disclosed. In some embodiments, for each image of a set of images associated with a scene, image pixels are divided into a plurality of pixel blocks, the pixel blocks are transformed into an arbitrary perspective, and pixels of an image array comprising the arbitrary perspective are populated with corresponding pixels from the transformed pixel blocks. An output image of the scene comprising the arbitrary perspective is then generated based at least in part on the populated image array.

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 has an overlapping field of view with at least one other image in the subset, 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.

Abstract: Techniques for generating an arbitrary perspective of a composite object are disclosed. In some embodiments, a specification of an orthographic view of a composite object comprises combined orthographic views of a plurality of objects, and an arbitrary perspective of the composite object is at least in part generated by populating the arbitrary perspective of the composite object with pixels harvested from existing images of the plurality of objects.

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: 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 from a plurality of other existing views are disclosed. In some embodiments, arbitrary view generation includes storing a set of images comprising a plurality of perspectives of an asset in a database and generating an image comprising a desired arbitrary perspective of the asset that is different than any of the plurality of perspectives by combining pixels comprising at least a subset of the set of images.

Abstract: Techniques for generating an arbitrary view from a plurality of other existing views are disclosed. In some embodiments, arbitrary view generation includes transforming each of a set of images of a scene into a requested perspective, wherein the set of images comprises perspectives that are different than the requested perspective, and generating an image of the scene comprising the requested perspective based at least in part on pixels harvested from the transformed set of images.

Abstract: Techniques for generating an arbitrary ensemble view from a plurality of other existing views are disclosed. In some embodiments, arbitrary view generation comprises retrieving a set of views corresponding to each of a plurality of objects, transforming the set of views of each of the plurality of objects to a requested perspective, and generating an ensemble view comprising the plurality of objects that has the requested perspective by combining pixels from the transformed sets of views of the plurality of objects.

Abstract: Adaptive sampling of pixels is disclosed. In some embodiments, an initial rendering of a scene that determines texture at each portion of the scene is generated, and a ray traced rendering of the scene is generated by tracing an initial sample of rays. The following steps are iterated until all portions of the ray traced rendering satisfy a noise threshold: subtract the initial rendering of the scene from the ray traced rendering of the scene to determine a measure of noise at each portion of the ray traced rendering and trace another sample of rays in the ray traced rendering for each portion of the ray traced rendering that does not satisfy the noise threshold. The completed ray traced rendering is outputted. Different portions of the completed ray traced rendering are sampled with different numbers of samples of rays.