A de-interlacing processing method, a de-interlacing processing device and a computer-readable storage medium are provided. The method includes acquiring image content characteristic information of a pixel point to be interpolated; and determining according to the image content characteristic information whether a de-interlacing algorithm based on motion adaptive or a de-interlacing algorithm based on motion compensation is adopted to perform de-interlacing processing.

A method for motion estimation, a non-transitory computer-readable storage medium, and an electronic device are provided. The method includes the following. An error between a block to be matched and each of reference blocks is determined to obtain multiple errors. At least one candidate block is determined from the reference blocks according to the multiple errors. A random number range is determined according to a displacement between the block to be matched and each of the reference blocks. Random motion vectors are obtained by using a motion vector between the block to be matched and each of the at least one candidate block as a basic motion vector and random numbers within the random number range as increments. A target motion vector corresponding to the block to be matched is determined according to the random motion vectors.

Systems, apparatuses, methods, and computer program products are disclosed for providing continuous session authentication and monitoring. An example method includes authenticating, at a first time, a session for a user of the client device based on an authentication image data structure and a plurality of first video frames captured before the first time. The example method further includes extracting sample data from a monitor region for each of a plurality of second video frames captured after the first time and generating motion data based on the extracted sample data. The example method further includes detecting, at a second time, a re-authentication trigger event based on the motion data. Subsequently, the example method includes re-authenticating the session based on the authentication image data structure and a plurality of third video frames captured after the second time.

Positions of an image capture device during capture of a video may be transferred to a computing device before the video is transferred to the computing device. The positions of the image capture device may be used to determine a viewing window for the video before the video is obtained. The viewing window may be used to present a stabilized view of the video when the video is obtained. For example, a stabilized view of the video may be presented as the video is streamed to the computing device.

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.

Computer processor hardware receives zone information specifying multiple elements of a rendition of a signal belonging to a zone. The computer processor hardware also receives motion information associated with the zone. The motion information can be encoded to indicate to which corresponding element in a reference signal each of the multiple elements in the zone pertains. For each respective element in the zone as specified by the zone information, the computer processor hardware utilizes the motion information to derive a corresponding location value in the reference signal; the corresponding location value indicates a location in the reference signal to which the respective element pertains.

The present disclosure relates to a motion compensation method and module, a chip, an electronic device, and a storage medium, to improve the problem of haloes easily appearing on the edges of moving objects.

The present disclosure is an apparatus and a method for providing a precise motion estimation learning model including, a database unit which stores a standard dataset labeled according to a first number of key points, an animation dataset labeled according to a second number of key points which is larger than the first number, and a photorealistic dataset having the second number of key points, a standard learning unit which learns the standard dataset for motion estimation to generate a standard learning model, an animation learning unit which retrains the animation dataset based on a weight of the standard learning model to generate an animation learning model, and a motion estimation learning unit which trains the photorealistic dataset based on the weight of the animation learning model to finely tune to generate a precise motion estimation learning model.

Apparatuses, systems, and techniques to interpolate one or more intermediate images from two or more images is disclosed. In at least one embodiment, a processor includes one or more circuits to interpolate one or more intermediate images from two or more images based, at least in part, on one or more inconsistent flow vectors corresponding to the two or more images.

Computer processor hardware receives a first set of adjustment values. The first set of adjustment values specify adjustments to be made to a predicted rendition of a signal generated at a first level of quality to reconstruct a rendition of the signal at the first level of quality. The computer processor hardware processes the first set of adjustment values and derives a second set of adjustment values based on the first set of adjustment values and a rendition of the signal at a second level of quality. The second level of quality is lower than the first level of quality.