Huawei Technologies Co., Limited

Friedrich-Alexander-Universität Erlangen-Nürnberg

Huawei Technoloiges Co., Ltd.

Elena Alexandrovna Alshina

Semih Esenlik

Anand Meher Kotra

Biao Wang

Sergey Yurievich Ikonin

Roman Igorevich Chernyak

Han Gao

Alexander Alexandrovich Karabutov

Timofey Mikhailovich Solovyev

Alexey Konstantinovich Filippov

Vasily Alexeevich Rufitskiy

Huanbang Chen

Jianle Chen

Haitao Yang

Maxim Borisovitch Sychev

Max Blaeser

Zhijie Zhao

Hu Chen

Victor Alexeevich Stepin

Weiwei Xu

Quanhe Yu

Marat Ravilevich Gilmutdinov

Eckehard Steinbach

Atanas Boev

Mikhail Vyacheslavovich Sosulnikov

Anton Igorevich Veselov

Rafal Mantiuk

Dmitry Yurievich Kuryshev

Yichuan Wang

Kirill Aleksandrovich Malakhov

Dmitry Vadimovich Novikov

Nickolay Dmitrievich Egorov

André Kaup

Fabian Brand

Kai Cui

Nikita Vyacheslavovich Ustiuzhanin

Kamilla Railevna Davletshina

Panqi Jia

Jürgen Seiler

Disclosed herein are methods and systems for encoding a picture and decoding a bitstream that may represent an encoded picture. During encoding and decoding, rescaling operations are applied to rescale an input to a size that can be processed by a layer of a neural network. Embodiments disclosed herein provide methods for rescaling that achieve a reduced size of the bitstream, thereby improving compression.

Method and apparatus for encoding or decoding a picture using a neural network

A method for coding a video implemented in an encoder or a decoder including the enhanced interpolation filter, EIF, for motion compensation, the method comprising: i) determining control point motion vectors, CPMVs, for a block according to affine inter-prediction, the block being an affine block or a sub-block of the affine block; ii) for a predefined sub-block size determining a reference area for a sub-block with the predefined sub-block size according to values of the CPMVs; iii) comparing the determined reference area with a predefined threshold; iv) applying EIF for motion compensation, comprising deriving the pixel-based motion vector field for the block; wherein if the determined reference area is larger than the threshold, deriving the pixel-based motion vector field for the block further comprises motion vector clipping, wherein motion vector clipping range is determined based on motion model of the block and the size of the block.

Affine motion model restrictions for memory bandwidth reduction of enhanced interpolation filter

This application provides a high dynamic range HDR video processing method, an encoding device, and a decoding device. The method includes: obtaining dynamic metadata of an NHDR video frame according to a dynamic metadata generation algorithm; calculating a tone-mapping (tone-mapping) curve parameter of the NHDR video frame based on the dynamic metadata of the NHDR video frame; generating a tone-mapping curve based on the curve parameter; determining, according to a quality assessment algorithm, distortion D' caused by the tone-mapping curve; comparing D′ and D, to determine a mode used by the NHDR video frame, where the mode is an automatic mode or a director mode, and Dis a threshold value; and determining metadata of the NHDR video frame based on the determined mode used by the NHDR video frame.

High dynamic range HDR video processing method, encoding device, and decoding device

The present disclosure provides an encoding method, wherein the method comprises: determining syntax elements to be coded, wherein the syntax elements include a reference picture list structure and at least one high-level syntax (HLS) weighted prediction parameters; coding the at least one HLS weighted prediction parameters; and after coding the at least one HLS weighted prediction parameters, coding the reference picture list structure. The syntax elements are reordered such that coding the reference picture list structure can be based on values of the at least one HLS weighted prediction parameters.

Method and apparatus of high-level signaling for weighted prediction

A system and method of decoding of a video or picture bitstream implemented by a decoding device are described. The bitstream can include data representing a current video coding layer. Furthermore, when determining that the current video coding layer is the only one layer in the bitstream, the method can include using the identifier of a NAL unit of the current video coding layer as the identifier of the current video coding layer.

Encoder, decoder and corresponding methods for improved compression ratios

The present disclosure relates generally to the field of video processing, and more particularly to high dynamic range (HDR) video and image processing. In particular, the present disclosure relates to determining one or more curve parameters of a tone mapping curve. For example, a device (encoder or decoder) may obtain a high dynamic range (HDR) video frame and metadata associated to the HDR video frame. The device further obtains a pair of anchor points, based on the HDR video frame and the metadata. The pair of anchor points comprises a first anchor point and a second anchor point of the tone mapping curve. Moreover, the device generates the one or more curve parameters of the tone mapping curve based on the pair of anchor points.

Encoder, decoder, system, and method for determining tone mapping curve parameters

A method and apparatus for decoding data for still or video processing into a bitstream are provided. In particular, two or more sets of feature map elements are obtained from the bitstream. Each set of feature map elements relates to a feature map. Each of the two or more sets of feature map elements is then respectively inputted into two or more feature map processing layers out of a plurality of cascaded layers. The decoded data for picture or video processing is then obtained as a result of the processing by the plurality of cascaded layers. According to the present disclosure, the data may be decoded from the bitstream in an efficient manner in the layered structure.

Method and apparatus for decoding with signaling of feature map data

A method of coding implemented by a decoding device, comprising obtaining a bitstream; obtaining a value of an indicator for a current block according to the bitstream; obtaining a value of a first parameter for the current block and a value of a second parameter for the current block, according to the value of the indicator and a predefined lookup table; obtaining a value of a sample distance for a sample which is located in the current block, according to the value of the first parameter and the value of the second parameter; obtaining a prediction value for the sample, according to the value of the sample distance for the sample.

Encoder, decoder and corresponding methods for sub-block partitioning mode

A method of coding is implemented by a decoding device, the method includes: receiving a bitstream, and obtaining from the bitstream, a first luma bit depth value of luma samples of a current picture. The method also includes performing a Hadamard Transform Domain Filtering (HTDF) post reconstruction filtering of a block of the current picture by using a lookup table based on the obtained first luma bit depth value.

Method and apparatus for hadamard transform domain filtering of the video signal with various bit depth

A method of coding implemented by a decoding device, comprising obtaining a value of a parameter for a current block, the value of the parameter indicating a partition mode for the current block; obtaining a first prediction mode for the current block; obtaining a second prediction mode for the current block; generate a first prediction value for a chroma sample in the current block according to the first prediction mode; generate a second prediction value for a chroma sample in the current block according to the second prediction mode; obtaining a combined prediction value by combining the first prediction value and the second prediction value.

Chroma sample weight derivation for geometric partition mode

The present disclosure provides a method of coding implemented by a decoding device, the method comprising: obtaining a value of a splitting mode index for a current coding block; obtaining a value of an angle index for the current coding block according to the value of the splitting mode index value and a pre-stored table; setting a value of an index partIdx according to the value of the angle index; and storing motion information for the current coding block according to the value of the index partIdx.

Coding process for geometric partition mode

An inter prediction method includes determining whether a non-rectangular inter prediction mode is allowed for a group of blocks; obtaining one or more inter prediction mode parameters and weighted prediction parameters for the group of blocks; and obtaining prediction value of a current block based on the one or more inter prediction mode parameters and weighted prediction parameters, wherein one of the inter prediction mode parameters indicates reference picture information for the current block, and wherein the group of blocks comprises the current block.

Method and apparatus of harmonizing weighted prediction with non-rectangular merge modes

Signalling of syntax elements in a sequence parameter set of a video bitstream is addressed. Particularly, it is provided a method of decoding a video bitstream wherein a sequence parameter set, SPS, is coded that contains syntax elements that apply to a video sequence, the method comprising obtaining a value of a first syntax element from the SPS used to specify whether a decoded picture buffer, DPB, parameters syntax structure is present in the SPS and obtaining a value of a second syntax element from the SPS, at least when determining that the value of the first syntax element specifies that the DPB parameters syntax structure is present in the SPS, used to specify the presence of a DPB syntax element in the DPB parameters syntax structure, wherein the DPB syntax element is applied to a temporal sublayer except for the highest temporal sublayer in the video sequence.

Encoder, a decoder and corresponding methods of signaling and semantics in parameter sets

A method for an intra predicting process of a video block is provided. The method comprises: obtaining a predicted sample value for a sample of the current coding block; obtaining a scaling factor value according to an intra prediction mode for the current coding block, and according to a height of the current coding block and/or a width of the current coding block; determining a first weight based on the scaling factor value; determining a second weight based on the scaling factor value; calculating an additional value as a weighted sum of a top reference sample value and a left reference sample value, by weighting the top reference sample value with the first weight and weighting the left reference sample value with the second weight; obtaining a modified predicted sample value according to the additional value and the predicted sample value; and outputting the modified predicted sample.

Prediction combination for oblique directional intra prediction

The present disclosure relates to an apparatus and a method for providing a plurality of motion vectors related to an image coded in a bitstream. The method includes obtaining a set of sample positions within the image, obtaining respective motion vectors associated with the set of sample positions, deriving an additional motion vector based on information coded in the bitstream, determining an additional sample position located within a triangle, which is formed by three sample positions of the set of sample positions, based on the respective motion vectors associated with the three sample positions, the triangle not including the rest of the sample positions of the set of sample positions, adding the additional sample position to the set of sample positions, and associating the derived additional motion vector with the additional sample position.

Growing community of inventors

Munich, Germany

Elena Alexandrovna Alshina