The embodiments herein provide a method of obtaining a weighted combination of dynamic vision sensor (DVS) measurements and contact image sensor (CIS) measurements for determining visual inference in an electronic device, the method includes receiving, by the electronic device, a DVS image and a CIS image from the image sensor; determining, by the electronic device, a plurality of parameters associated with the DVS image and feature velocities of a plurality of CIS features present in the CIS image; determining, by the electronic device, a determined DVS feature confidence based on the plurality of parameters associated with the DVS image; determining, by the electronic device, a determined CIS feature confidence based on the feature velocities of the plurality of features present in the CIS image; and calculating, by the electronic device, a weighted visual inference based on the determined DVS feature confidence and the determined CIS feature confidence.

Techniques for tuning an image editing operator for reducing a distractor in raw image data are presented herein. The image editing operator can access the raw image data and a mask. The mask can indicate a region of interest associated with the raw image data. The image editing operator can process the raw image data and the mask to generate processed image data. Additionally, a trained saliency model can process at least the processed image data within the region of interest to generate a saliency map that provides saliency values. Moreover, a saliency loss function can compare the saliency values provided by the saliency map for the processed image data within the region of interest to one or more target saliency values. Subsequently, the one or more parameter values of the image editing operator can be modified based at least in part on the saliency loss function.

A distributed, cross reality system efficiently and accurately compares location information that includes image frames. Each of the frames may be represented as a numeric descriptor that enables identification of frames with similar content. The resolution of the descriptors may vary for different computing devices in the distributed system based on degree of ambiguity in image comparisons and/or computing resources for the device. A descriptor computed for a cloud-based component operating on maps of large areas that can result in ambiguous identification of multiple image frames may use high resolution descriptors. High resolution descriptors reduce computationally intensive disambiguation processing. A portable device, which is more likely to operate on smaller maps and less likely to have the computational resources to compute a high resolution descriptor, may use a lower resolution descriptor.

Systems and methods generating a haptic output response are disclosed. Video content is displayed on a display. A location of a user touch on the display is detected while the video content is being displayed. A region of interest in the video content is determined based on the location of the user touch. And a haptic output response is generated to a user. A characteristic of the haptic output response is determined using one or more characteristics of the region of interest.

A method for determining authenticity of a document is provided that includes receiving, by an electronic device, an image of a document, assigning a label to the image, and obtaining vectors for each image in a subset of images. Each image is of a document and is assigned the same label as the received image. Moreover, the method includes encoding the received image into a vector, calculating a distance between the vector of the received image and each obtained vector, comparing each of the calculated distances against a threshold distance, and calculating a number of the calculated distances that are less than or equal to the threshold distance. In response to determining the calculated number is at least equal to a required number, the document in the received image is determined to be authentic. Otherwise, the received image requires manual review.

A method for stabilization of a video sequence captured by an electronic device is provided. The method includes identifying a subject in the video sequence, estimating a velocity of the subject relative to the electronic device, determining a point of view of a subject in the video sequence with respect to the electronic device and the velocity of the subject relative to the electronic device and stabilizing the video sequence based on the determined point of view.

A method for stabilization of a video sequence captured by an electronic device is provided. The method includes identifying a subject in the video sequence, estimating a velocity of the subject relative to the electronic device, determining a point of view of a subject in the video sequence with respect to the electronic device and the velocity of the subject relative to the electronic device and stabilizing the video sequence based on the determined point of view.

A technique for detecting a glitch in an image is provided. The technique includes providing an image to a plurality of individual classifiers to generate a plurality of individual classifier outputs and providing the plurality of individual classifier outputs to an ensemble classifier to generate a glitch classification.

A mobile client device is localized based on a captured image by identifying where the client device is located from a set of known locations. The set of known locations is associated with a set of regions, where each region is associated with a set of key frames representing the important features of the region. Latent vectors and keypoints are calculated for each of the key frames and an image captured by the client device. The system compares the latent vectors of the captured image to the latent vectors associated with the regions to determine a subset of similar regions. The system compares the keypoints of the captured image to the keypoints associated with the regions in the subset to determine a best match. This determined location is considered the region of the client device and may be used with other localization information to maintain localization of the client device.

A method for efficient image registration between two images in the presence of inlier-poor domains includes receiving a set of candidate correspondences between the two images. An approximate homography between the two images is generated based upon a first correspondence in the correspondences. The set of candidate correspondences is filtered to identify inlier correspondences based upon the approximate homography. A candidate homography is computed based upon the inlier correspondences. The candidate homography can be selected as a final homography between the two images based upon a support of the candidate homography against the set of candidate correspondences. An image registration is performed between the two images based upon the candidate homography being selected as the final homography.