The present disclosure relates to methods and devices for performing depth estimation on image data. In one example, a device performs depth estimation on first and second images captured using one or more cameras having a color filter array. Each, image of the first and second images comprises multiple color channels. Each color channel of the multiple color channels corresponds to a respective color channel of the color filter array.sub.. The, device performs the depth estimation by estimating disparity from the color channels of the first and second images.

In some aspects, the techniques described herein relate to systems, methods, and computer readable media for data pre-processing for stereo-temporal image sequences to improve three-dimensional data reconstruction. In some aspects, the techniques described herein relate to systems, methods, and computer readable media for improved correspondence refinement for image areas affected by oversaturation. In some aspects, the techniques described herein relate to systems, methods, and computer readable media configured to fill missing correspondences to improve three-dimensional (3-D) reconstruction. The techniques include identifying image points without correspondences, using existing correspondences and/or other information to generate approximated correspondences, and cross-checking the approximated correspondences to determine whether the approximated correspondences should be used for the image processing.

A special test target may enable standardized testing of performance of image based depth measuring systems. In addition, the error in measured depth with respect to the ground truth may be used as a metric of system performance. This test target may aid in identifying the limitations of the disparity estimation algorithms.

An imagery processing system determines pixel color values for pixels of captured imagery from volumetric data, providing alternative pixel color values. A main imagery capture device, such as a camera, captures main imagery such as still images and/or video sequences, of a live action scene. Alternative devices capture imagery of the live action scene, in some spectra and form, and capture information related to pixel color values for multiple depths of a scene, which can be processed to provide reconstruction.

This disclosure relates to techniques for generating robust depth estimations for captured images using semantic segmentation. Semantic segmentation may be defined as a process of creating a mask over an image, wherein pixels are segmented into a predefined set of semantic classes. Such segmentations may be binary (e.g., a ‘person pixel’ or a ‘non-person pixel’) or multi-class (e.g., a pixel may be labelled as: ‘person,’ ‘dog,’ ‘cat,’ etc.). As semantic segmentation techniques grow in accuracy and adoption, it is becoming increasingly important to develop methods of utilizing such segmentations and developing flexible techniques for integrating segmentation information into existing computer vision applications, such as depth and/or disparity estimation, to yield improved results in a wide range of image capture scenarios. In some embodiments, an optimization framework may be employed to optimize a camera device's initial scene depth/disparity estimates that employs both semantic segmentation and color regularization in a robust fashion.

A wearable electronic device includes a left-eye display configured to output light of a first color corresponding to a 3D left-eye image, a right-eye display configured to output light of a second color corresponding to a 3D right-eye image, a left-eye optical waveguide configured to adjust a path of the light of the first color and output the light of the first color, a right-eye optical waveguide configured to adjust a path of the light of the second color and output the light of the second color, a left-eye display control circuit configured to supply a driving power and a control signal to the left-eye display, a right-eye display control circuit configured to supply a driving power and a control signal to the right-eye display, a communication module configured to communicate with a mobile electronic device, and a second control circuit configured to supply a driving power and a control signal to the communication module.

Aspects of the present disclosure relate to distributed virtual reality. In examples, a depth buffer and a color buffer are generated at a presenter device as part of rendering a virtual environment. The virtual environment may be perceived by a user in three dimensions (3D), for example via a virtual reality (VR) headset. Virtual environment information comprising the depth buffer and the color buffer may be transmitted to a viewer device, where it is used to render the virtual environment for display to a viewer. For example, the viewer may similarly view the virtual environment in 3D via a VR headset. A viewer perspective (e.g., from which the virtual environment is generated for the viewer) may differ from a presenter perspective and may be manipulated by the viewer, thereby decoupling the viewer's perception of the virtual environment from that of the presenter.

A method for generating a three-dimensional (3D) lane model, the method including calculating a free space indicating a driving-allowed area based on a driving image captured from a vehicle camera, generating a dominant plane indicating plane information of a road based on either or both of depth information of the free space and a depth map corresponding to a front of the vehicle, and generating a 3D short-distance road model based on the dominant plane.

A method of displaying stereoscopic information related to an ultrasound sectional plane of a target object includes setting a line of interest on the ultrasound sectional plane of the target object based on a received input; obtaining an ultrasound signal of the ultrasound sectional plane of the target object along the set line of interest; converting the obtained ultrasound signal to represent the stereoscopic information in a three-dimensional manner; and displaying the stereoscopic information related to the ultrasound sectional plane of the target object.

Systems and method for correcting images including artifacts due to dirty camera lenses of electronic device are disclosed. Correction of images by the systems and methods includes obtaining a first raw pixel image of a scene captured with a first camera, obtaining a second raw image of the scene captured with a second camera separate from the first camera in a camera baseline direction, rectifying the first and second raw pixel images to create respective first and second rectified pixel images, determining disparity correspondence between corresponding image pixel pairs of the first and second rectified images in the camera baseline direction, mapping first and second rectified images into the same domain using the determined disparity, detect image artifact regions within each domain mapped image by comparing corresponding regions of the domain mapped images, determining correction factors for each detected image artifact region, and correcting the rectified first and second images by applying the determined correction factors.