Abstract: A method for image enhancement includes capturing multiple input images of a scene, including at least a first input image having a first field of view (FOV) captured with a first focal depth and a second input image having a second FOV captured with a second focal depth. The input images in the sequence are preprocessed so as to align the images. The aligned images are processed in a neural network, which generates an output image having an extended depth of field encompassing at least the first and second focal depths.

Abstract: A system for collaborative video recording is described. The system may include a reference clock configured to track a reference time. The system may provide, to a plurality of recording devices, a synchronization code for a collaborative video recording session. The system may identify the plurality of recording devices as participants in the collaborative video recording session. The collaborative video recording session may include broadcasting one or more synchronization signals to synchronize the plurality of recording devices to the reference time tracked by the reference clock. The collaborative video recording session may include receiving a plurality of videos from the plurality of recording devices, wherein the plurality of videos comprise timestamps based on synchronization to the reference time. The collaborative video recording session may include generating a shared timeline for the plurality of videos, wherein the shared timeline synchronizes the timestamps between the plurality of videos.

Abstract: A processing pipeline and method for mixed reality systems that utilizes selective auto-exposure for a region of interest in a scene based on gaze and that compensates exposure for the rest of the scene based on ambient lighting information for the scene. Images may be generated for display that provide an exposure-compensated, foveated high dynamic range (HDR) experience for the user.

Abstract: A processing pipeline and method for mixed reality systems that utilizes selective auto-exposure for a region of interest in a scene based on gaze and that compensates exposure for the rest of the scene based on ambient lighting information for the scene. Images may be generated for display that provide an exposure-compensated, foveated high dynamic range (HDR) experience for the user.

Abstract: In one implementation, a method includes obtaining an image. The method includes generating a plurality of denoised images by denoising the image using a respective plurality of denoisers, wherein the plurality of denoisers includes a first denoiser associated with a first level of exposure and a second denoiser associated with a second level of exposure. The method includes generating a combined image by combining the plurality of denoised images.

Abstract: In an exemplary process, a set of parameters corresponding to characteristics of a physical setting of a user is obtained. Based on the parameters, at least one display placement value and a fixed boundary location corresponding to the physical setting are obtained. In accordance with a determination that the at least one display placement value satisfies a display placement criterion, a virtual display is displayed at the fixed boundary location corresponding to the physical setting.