A head-mounted device may have a head-mounted housing. Optical components may be supported by the head-mounted housing. The optical components may include cameras such as front-facing cameras and/or movable optical modules that have displays for displaying images to eye boxes. Sensors may be provided in the head-mounted device to detect changes in orientation between respective optical modules, between respective portions of a chassis, display cover layer, or other head-mounted support structure in the housing, between optical components such as cameras, and/or between optical components and housing structures. Information from these sensors can be used to measure image misalignment such as image misalignment associated with misaligned cameras or misalignment between optical module images and corresponding eye boxes.

Wearable head-mounted displays, such as virtual reality systems, present immersive experiences and environments to a wearer. However, the head-mounted displays, as well as the immersive environments that they produce, limit the wearer's ability to interact with outside observers. For example, a wearer may not be able to see outside observers, and outside observers may not have any insight to what the wearer is experiencing or where the wearer's attention is directed. Accordingly, a wearable electronic device may include an outward-facing display configured to display information to outside observers, such as images of the wearer's face or images that represent or indicate the state of the wearer and/or the head mounted display.

A system and method of calibrating a broadcast video feed are disclosed herein. A computing system retrieves a plurality of broadcast video feeds that include a plurality of video frames. The computing system generates a trained neural network, by generating a plurality of training data sets based on the broadcast video feed and learning, by the neural network, to generate a homography matrix for each frame of the plurality of frames. The computing system receives a target broadcast video feed for a target sporting event. The computing system partitions the target broadcast video feed into a plurality of target frames. The computing system generates for each target frame in the plurality of target frames, via the neural network, a target homography matrix. The computing system calibrates the target broadcast video feed by warping each target frame by a respective target homography matrix.

System, methods, and other embodiments described herein relate to an improved approach to training a depth model to derive depth estimates from monocular images using cost volumes. In one embodiment, a method includes predicting, using a depth model, depth values from at least one input image that is a monocular image. The method includes generating a cost volume by sampling the depth values corresponding to bins of the cost volume. The method includes determining loss values for the bins of the cost volume. The method includes training the depth model according to the loss values of the cost volume.

Systems and methods for machine learning based controllable animation of still images is provided. In one embodiment, a still image including a fluid element is obtained. Using a flow refinement machine learning model, a refined dense optical flow is generated for the still image based on a selection mask that includes the fluid element and a dense optical flow generated from a motion hint that indicates a direction of animation. The refined dense optical flow indicates a pattern of apparent motion for the at least one fluid element. Thereafter, a plurality of video frames is generated by projecting a plurality of pixels of the still image using the refined dense optical flow.

Computer vision systems and methods for noisy contour alignment are provided. The system generates a loss function and trains a convolutional neural network with the loss function and a plurality of images of a dataset to learn to align contours with progressively increasing complex forward and backward transforms over increasing scales. The system can align an attribute of an image of the dataset by the trained neural network.

A method for enhancing a wide angle image to improve the perspectives and the visual appeal thereof wide-angle images uses custom adaptive dewarping. The method is based on the scene image content of recognized objects in the image, the position of these objects in the image, the depth of these objects in the scene with respect to other objects and the general context of the image.

The present disclosure relates to a method and device for image correction and a storage medium. The method can include a correction offset for each unit to be corrected in an image is determined, at least one target region in the image is determined, an image weight coefficient for each unit to be corrected in the image is determined according to the at least one target region, a final offset for each unit to be corrected in the image is determined according to the image weight coefficient and the correction offset, and each unit to be corrected in the image is corrected according to the final offset.

Systems, methods, and computer-readable media for context-aware synthesis for video frame interpolation are provided. Bidirectional flow may be used in combination with flexible frame synthesis neural network to handle occlusions and the like, and to accommodate inaccuracies in motion estimation. Contextual information may be used to enable frame synthesis neural network to perform informative interpolation. Optical flow may be used to provide initialization for interpolation. Other embodiments may be described and/or claimed.

A mobile device, such as a smart phone, is provided with a camera. Digital content displayed on display screen of the mobile device may be manipulated in response to natural movements of the mobile device by a user. Motion of the mobile device is detected relative to a nearby textured surface by analyzing images of the textured surface. The displayed digital content is manipulated in response to the detected motion of the mobile device.