Intel Corporation

Huawei Technologies Co., Limited

Anton Veselov

Marat Gilmutdinov

Elena Alexandrovna Alshina

Andrey Mikhailovich Turlikov

Marat Ravilevich Gilmutdinov

Ramanathan Sethuraman

Jean-Pierre Giacalone

Aleksandar Beric

Zdravko Pantic

Vladimir Kovacevic

Anton Valerievich Sergeev

Dmitry Vadimovich Novikov

Kirill Aleksandrovich Malakhov

Ivan Nikolaevich Grokhotkov

Nikita Vyacheslavovich Ustiuzhanin

Nickolay Dmitrievich Egorov

A method and device for digital signal processing are provided, particularly relating to video image processing. The device obtains image data comprising a plurality of pixels. The image data comprises a plurality of sequentially captured images. The device estimates, for a target image, a set of backward motion vector fields (backward MVFs) based on the target image, and a first set of images captured before the target image. The device further estimates a set of forward MVFs based on the target image and a second set of images captured after the target image. Depending on the estimating for the target image, the device generates an output image based on a merging procedure of the target image and the first set of images and the set of backward MVFs, and/or the second set of images and the set of forward MVFs.

Devices and methods for digital signal processing

An image processing apparatus processes a color filter mosaic, CFM, image of a scene into a final image of the scene. The image processing apparatus includes processing circuitry configured to implement a neural network. The neural network is configured to process the CFM image into an enhanced CFM image. The processing circuitry is further configured to transform the enhanced CFM image into the final image.

Image processing apparatus and method implementing a neural network to pre-process a CFM image for further process by ISP pipeline

Various embodiments are generally directed to techniques for determining whether to use an interpolated frame or repeat a base frame in up-converting the frame rate of a base video stream to generate an up-converted video stream. A device to up-convert a frame rate includes an analysis component to analyze a pair of temporally adjacent base frames and a motion vector associated with movement of an object between the pair of base frames to determine a degree of visual artifacts involving an edge of the object in an interpolated frame, and a selection component to compare the degree of visual artifacts to a threshold and select the interpolated frame for insertion between the preceding base frame and the following base frame in up-converting a frame rate of the base video stream to generate an up-converted video stream based on the comparison. Other embodiments are described and claimed.

Techniques for frame repetition control in frame rate up-conversion

Methods, apparatus, systems and articles of manufacture to perform block-based static region detection for video processing are disclosed. Disclosed example video processing methods include segmenting pixels in a first frame of a video sequence into a first plurality of pixel blocks. Such example methods can also include processing the first plurality of pixel blocks and a second plurality of pixel blocks corresponding to a prior second frame of the video sequence to create, based on a first criterion, a map identifying one or more static pixel blocks in the first plurality of pixel blocks. Such example methods can further include identifying, based on the map, a static region in the first frame of the video sequence.

Block-based static region detection for video processing

Information to be transmitted may be compressed using range coding for adaptive arithmetic coding with a virtual sliding window. Cost and complexity of coding may be reduced in some cases.

Compression using range coding with virtual sliding window

An artifact in a discrete cosine transform based decoder output may be detected by developing a set of templates. An average intensity within each block in a reconstructed picture is calculated (). The differences of each pixel value from the average output intensity within each block is determined (). That difference is then multiplied by one of the templates within each block and the results of the multiplications are summed to obtain a calculated result (). The calculated result is then compared to a threshold to detect an artifact such as ringing or mosquito noise artifacts ().

Detecting artifacts in quantization noise in images compresses using discrete cosine transforms

Growing community of inventors

Saint-Petersburg, Russia

Anton Veselov