Abstract:
Systems and methods for aligning ground based images of a geographic area taken from a perspective at or near ground level and a set of aerial images taken from, for instance, an oblique perspective, are provided. More specifically, candidate aerial imagery can be identified for alignment with the ground based image. Geometric data associated with the ground based image can be obtained and used to warp the ground based image to a perspective associated with the candidate aerial imagery. One or more feature matches between the warped image and the candidate aerial imagery can then be identified using a feature matching technique. The matched features can be used to align the ground based image with the candidate aerial imagery.
Abstract:
In one aspect, one or more computing devices receive a set of image frames. Each image frame includes pixels. The computing devices align image frames in order to identify flows of the pixels in the set of image frames. Regions of bokeh effect are identified in each image frame by measuring the sizes of areas of expansion across image frames using a set of assumptions and the identified flows. The computing devices adjust the alignment of the set of image frames based at least in part on the identified regions of bokeh effect. For each image frame, the computing devices generates an index map of focus values for each of the pixels that image frame using the improved alignment. A depth map is generated by the computing devices based at least in part on the index maps.
Abstract:
Systems and methods for generating depth data from images captured by a camera-enabled mobile device are provided. The depth data can be used to refocus one or more portions of an image captured by the camera-enabled mobile device. A user can select different portions of the captured image to bring different portions of the image into focus and out of focus. Depth data for an image can be generated from a reference image and a sequence of images captured by the image capture device. The sequences of images can be acquired using a suitable camera motion. A refocused image can be generated with portions of the image out of focus relative to the reference image.
Abstract:
Systems and methods for aligning ground based images of a geographic area taken from a perspective at or near ground level and a set of aerial images taken from, for instance, an oblique perspective, are provided. More specifically, candidate aerial imagery can be identified for alignment with the ground based image. Geometric data associated with the ground based image can be obtained and used to warp the ground based image to a perspective associated with the candidate aerial imagery. One or more feature matches between the warped image and the candidate aerial imagery can then be identified using a feature matching technique. The matched features can be used to align the ground based image with the candidate aerial imagery.
Abstract:
Systems and methods for capturing omnistereo content for a mobile device may include receiving an indication to capture a plurality of images of a scene, capturing the plurality of images using a camera associated with a mobile device and displaying on a screen of the mobile device and during capture, a representation of the plurality of images and presenting a composite image that includes a target capture path and an indicator that provides alignment information corresponding to a source capture path associated with the mobile device during capture of the plurality of images. The system may detect that a portion of the source capture path does not match a target capture path. The system can provide an updated indicator in the screen that may include a prompt to a user of the mobile device to adjust the mobile device to align the source capture path with the target capture path.
Abstract:
Systems and methods are related to a camera rig and generating stereoscopic panoramas from captured images for display in a virtual reality (VR) environment.
Abstract:
Systems and methods for compressing a depthmap are provided. In some aspects, a system includes an encoding module configured to determine a minimum value and a maximum value of a depthmap. The encoding module is further configured to normalize the depthmap based on the minimum value, the maximum value, and an encoding model. The normalized depthmap includes a scalar value for each pixel of the depthmap. The system also includes a compression module configured to compress the normalized depthmap.
Abstract:
In one aspect, one or more computing devices receive a set of image frames. Each image frame includes pixels. The computing devices align image frames in order to identify flows of the pixels in the set of image frames. Regions of bokeh effect are identified in each image frame by measuring the sizes of areas of expansion across image frames using a set of assumptions and the identified flows. The computing devices adjust the alignment of the set of image frames based at least in part on the identified regions of bokeh effect. For each image frame, the computing devices generates an index map of focus values for each of the pixels that image frame using the improved alignment. A depth map is generated by the computing devices based at least in part on the index maps.
Abstract:
Systems and methods for aligning ground based images of a geographic area taken from a perspective at or near ground level and a set of aerial images taken from, for instance, an oblique perspective, are provided. More specifically, candidate aerial imagery can be identified for alignment with the ground based image. Geometric data associated with the ground based image can be obtained and used to warp the ground based image to a perspective associated with the candidate aerial imagery. One or more feature matches between the warped image and the candidate aerial imagery can then be identified using a feature matching technique. The matched features can be used to align the ground based image with the candidate aerial imagery.
Abstract:
Embodiments efficiently account for variations in camera position across an image, when the image is texture mapped from a single position associated with the image. In an embodiment, each pixel of an image is texture mapped to a three dimensional model. A time offset mask for the image and a value representing a speed of the camera are received. The time offset mask and speed values are used to create an offset mask. The offset mask is applied to the texture mapped model to correct for variations in camera position across an image.