Methods and apparatus provide cloud-based video encoding that generates encoded video data by one or more encoders in a cloud platform for a plurality of cloud encoding sessions. The methods and apparatus generate operational improvement tradeoff data in response to operational encoding metrics associated with the one or more encoders and change operational characteristics of the one or more encoders for at least one of the cloud encoding sessions based on the operational improvement tradeoff data.

Methods, apparatus and systems for video bitstream generation and parsing are described. One example method of video bitstream processing includes parsing a header at a video unit level in a video bitstream for a first field indicative of whether the video unit includes multiple network abstraction layer bit units having multiple types, parsing, due to determining that the video unit includes multiple network abstraction layer bit units having multiple types, a second field in the header indicative of whether the video unit comprises an intra random access point, and decoding, based on the first field and the second field, the video bitstream to generate a video.

Methods, apparatus and systems for video bitstream generation and parsing are described. One example method of video bitstream processing includes parsing a header at a video unit level in a video bitstream for a first field indicative of whether the video unit includes multiple network abstraction layer bit units having multiple types, parsing, due to determining that the video unit includes multiple network abstraction layer bit units having multiple types, a second field in the header indicative of whether the video unit comprises an intra random access point, and decoding, based on the first field and the second field, the video bitstream to generate a video.

Techniques are described herein for processing video data using a neural network system. For instance, a process can include generating, by a first convolutional layer of an encoder sub-network of the neural network system, output values associated with a luminance channel of a frame. The process can include generating, by a second convolutional layer of the encoder sub-network, output values associated with at least one chrominance channel of the frame. The process can include generating, by a third convolutional layer based on the output values associated with the luminance channel of the frame and the output values associated with the at least one chrominance channel of the frame, a combined representation of the frame. The process can further include generating encoded video data based on the combined representation of the frame.

An image encoding method is an image encoding method executed by an image encoding device, the method including: a feature map generating step of generating a first feature map representing a feature of an encoding target image which is an encoding target image and a second feature map representing a feature of the encoding target image at different resolutions; a correlation map generation step of generating a correlation map representing a correlation distribution between the first and second feature maps; a contraction function generation step of generating a contraction function which is a function used for a contraction process for a predetermined image in a decoding process based on the correlation map; and an encoding step of executing an encoding process on the contraction function and outputting a result of the encoding process.

A computer-readable recording medium storing a program that causes a computer to execute a process, the process includes specifying occurrence frequencies of respective gradation values with regard to pixels included in image data and represented by gradation values of a predetermined bit count; extracting a predetermined number of gradation values from a gradation value having a high occurrence frequency in a descending order; generating correspondence information for performing bit conversion of the extracted gradation values into coded values of a bit count in accordance with the predetermined number; and encoding the image data by performing bit conversion of first pixels having any one of the predetermined number of gradation values among the pixels based on the correspondence information, and performing bit conversion of second pixels having any one of gradation values other than the predetermined number of gradation values among the pixels.

A computer-readable recording medium storing a program that causes a computer to execute a process, the process includes specifying occurrence frequencies of respective gradation values with regard to pixels included in image data and represented by gradation values of a predetermined bit count; extracting a predetermined number of gradation values from a gradation value having a high occurrence frequency in a descending order; generating correspondence information for performing bit conversion of the extracted gradation values into coded values of a bit count in accordance with the predetermined number; and encoding the image data by performing bit conversion of first pixels having any one of the predetermined number of gradation values among the pixels based on the correspondence information, and performing bit conversion of second pixels having any one of gradation values other than the predetermined number of gradation values among the pixels.

In communication applications, aggregate source image data at a transmitter exceeds the data that is needed to display a rendering of a viewport at a receiver. Improved streaming techniques that include estimating a location of a viewport at a future time. According to such techniques, the viewport may represent a portion of an image from a multi-directional video to be displayed at the future time, and tile(s) of the image may be identified in which the viewport is estimated to be located. In these techniques, the image data of tile(s) in which the viewport is estimated to be located may be requested at a first service tier, and the other tile in which the viewport is not estimated to be located may be requested at a second service tier, lower than the first service tier.

In communication applications, aggregate source image data at a transmitter exceeds the data that is needed to display a rendering of a viewport at a receiver. Improved streaming techniques that include estimating a location of a viewport at a future time. According to such techniques, the viewport may represent a portion of an image from a multi-directional video to be displayed at the future time, and tile(s) of the image may be identified in which the viewport is estimated to be located. In these techniques, the image data of tile(s) in which the viewport is estimated to be located may be requested at a first service tier, and the other tile in which the viewport is not estimated to be located may be requested at a second service tier, lower than the first service tier.

A method, computer program, and computer system for video coding is provided. Video data including one or more quantized coefficients is received. One or more index values associated with the quantized coefficients are mapped to one or more step values based on an exponential mapping. The video data is decoded based on the one or more step values.