Tencent America LLC

Future Wei Technologies, Inc.

Innogrit Technologies Co., Ltd.

Huawei Technologies Co., Limited

Marvellworld Trade Ltd.

Logitech Europe S.a.

Nyquist Semiconductor Limited

Wei Jiang

Shan Liu

Wei W Wang

Wei Wang

Xiaozhong Xu

Lin Chen

Ding Ding

Sheng Lin

Gang Zhao

Zeqiang Li

Byeongdoo Choi

Wei D Wang

Jie Chen

Stephan Wenger

Shawn Chen

Jinwei Gu

Zining Wu

Hong Heather Yu

Zhenyu Wu

John Wus

Liqiang Wang

Xiao Wang

Christopher D Coley

Shiann-Ming Liou

Yan Chen

Lyndon Kennedy

Tao Wei

Bennett S Wilburn

Gareth James Selfe

Kangmin Hu

Siyu Qi

Hongsen Yu

Chiahung Chien

Kaidi Xu

Systems and methods for deep neural network (DNN)-based cross component prediction are provided. A method includes inputting a reconstructed luma block of an image or video into a DNN; and predicting, by the DNN, a reconstructed chroma block of the image or video based on the reconstructed luma block that is input. Luma and chroma reference information and side information may also be input into the DNN to predict the reconstructed chroma block. The various inputs may also be generated using processes such as downsampling and transformation.

DNN-based cross component prediction

Video processing with a multi-quality loop filter using a multi-task neural network is performed by at least one processor and includes generating a first set of masked weight parameters, based on an input and a plurality of quantization parameter values with a corresponding first set of masks and first plurality of weight parameters, for a first set of shared neural network layers, selecting a second set of task specific neural network layers for the plurality of quantization parameter values with a second plurality of weight parameters, based on the plurality of quantization parameter values, computing an inference output, based on the first set of masked weight parameters and the second plurality of weight parameters, and outputting the computed inference output as an enhanced result.

Multi-task neural network by micro-structured parameter sharing for multi-quality loop filter

A method and apparatus for adaptive neural image compression with smooth quality control by meta-learning includes receiving an input image and a target quality control parameter; generating quality-adaptive weight parameters of an encoding neural network using shared encoding parameters and adaptive encoding parameters; and encoding the input image, based on the target quality control parameter, using the encoding neural network with the quality-adaptive weight parameters, to generate a compressed representation.

Adaptive neural image compression with smooth quality control by meta-learning

A method, computer program, and computer system is provided for compressing a neural network model. A multi-dimensional tensor corresponding to a set of weight coefficients associated with a neural network is reshaped. A subset of weight coefficients is identified from among the set of weight coefficients. A model of the neural network is compressed based on the identified subset of weight coefficients.

Neural network model compression with quantizability regularization

Neural image compression using substitutional quality factor learning in a latent space, including receiving a compressed bitstream and a target quality factor indicating a target compression quality, calculating a decoded latent representation of the compressed bitstream, and calculating a reconstructed image based on the decoded latent representation of the compressed bitstream and the target quality factor, computing a shared feature based on a network forward computation using shared decoding parameters (SDP) of one or more layers of a convolutional neural network, computing estimated adaptive decoding parameters (ADP) for the one or more layers of the convolutional neural network based on the shared feature, the adaptive decoding parameters, and the target quality factor, and computing an output tensor based on the estimated ADP in the one or more layers of the convolutional neural network and the shared feature.

Substitutional quality factor learning in the latent space for neural image compression

The disclosure relates to technology for generating a compressed neural network. A weight tensor is received from a neural network to be compressed, and it is reordered to be compressed to have an inner two-dimensional (2D) shape and a 2D sparse bitmap. A layered structure is generated that represents the reordered weight tensor, and the reordered weight tensor is divided into a group of coefficients (GOCs). An encoding mode is selected to generate a quantized reordered weight tensor using one of a codebook or direct quantization, and a column swapped quantized reordered weigh tensor is generated. A compressed neural network is formed by encoding and the compressed representation of the neural network is transmitted to a target system for decompression.

Generating a compressed representation of a neural network with proficient inference speed and power consumption

Disclosed is a non-volatile memory and a system having a controller and two non-volatile memories. The two non-volatile memories are configured to communicate with the controller through a same channel, and to send respective status information thereof to the controller through a same line. The first non-volatile memory is configured to: determine whether the line is available for sending the status information; upon determining that the line is available, send an alert to the controller using a processor by driving the line to a first logic level for a first duration and stopping driving the line upon expiration of the first duration; upon expiration of the first duration, determine a logic level of the line; upon determining that the logic level of the line is a second logic level, send its status information to the controller through the line upon expiration of a second duration.

Non-volatile memory with an arbitration function on shared status channel

Neural network based substitutional end-to-end (E2E) image compression (NIC) being performed by at least one processor and includes receiving an input image to an E2E NIC framework, determining a step size of the input image indicating a learning rate of a training model, determining a substitute image based on the training model, encoding the substitute image in lieu of the input image to generate a bitstream, and mapping the substitute image to the bitstream to generate a compressed representation. Further, step size may be determined by a scheduler and change throughout the training of the training model. The image may also be split into patches for which a scheduler is assigned for each patch and each patch is encoded instead of the entire input image.

Method and apparatus for dynamic learning rates of substitution in neural image compression

A method of unification based coding for neural network model compression is performed by at least one processor and includes receiving a layer uniform flag indicating whether a quantized weight of an input neural network is encoded using a uniform coding method, and determining whether the quantized weight is encoded using the uniform coding method, based on the received layer uniform flag. The method further includes, based on the quantized weight being determined to be encoded using the uniform coding method, encoding the quantized weight, using the uniform coding method, and based on the quantized weight being determined to not be encoded using the uniform coding method, encoding the quantized weight, using a non-uniform coding method.

Method and apparatus for unification based coding for neural network model compression

A pruning method of neural network based video coding of a current block of a picture of a video sequence is performed by at least one processor and includes categorizing parameters of a neural network into groups, setting a first index to indicate that a first group of the groups is to be pruned, and a second index to indicate that a second group of the groups is not to be pruned, and transmitting, to a decoder, the set first index and the set second index. Based on the transmitted first index and the transmitted second index, the current block is processed using the parameters of which the first group of the groups is pruned.

Pruning methods for neural network based video coding

Systems and methods for encoding and decoding neural network data is provided. A method includes: obtaining an independent neural network with a topology; encoding the independent neural network with the topology such as to obtain a neural network representation (NNR) bitstream; and sending the NNR bitstream to a decoder, wherein the NNR bitstream includes a group of NNR units (GON) that represents the independent neural network with the topology, and the GON includes an NNR model parameter set unit, an NNR layer parameter set unit, an NNR topology unit, an NNR quantization unit, and an NNR compressed data unit.

Techniques for parameter set and header design for compressed neural network representation

Neural network based substitutional end-to-end (E2E) image compression (NIC) being performed by at least one processor and includes receiving an input image to an E2E NIC framework, determining a substitute image based on a training model of the E2E NIC framework, encoding the substitute image to generate a bitstream, mapping the substitute image to the bitstream to generate a compressed representation of the input image. Further, the input may be partitioned into blocks for which a substitute representation is determined for each block and each block is encoded instead of the entire substitute image.

Method and apparatus for multi-learning rates of substitution in neural image compression

A method, computer program, and computer system is provided for video encoding and decoding. Video data including a current picture is received. A virtual reference frame is generated for the current picture based on hierarchical level associated with the current picture and a nearest decoded picture. The video data is decoded based on the generated reference frame.

Utilizing hierarchical structure for neural network based tools in video coding

Systems and methods for block-wise entropy coding methods in neural image compression is provided. A method includes: receiving a bitstream that includes an image; partitioning the image into a plurality of blocks; compressing each of the plurality of blocks by a neural network-based encoder; obtaining compressed features by obtaining a compressed feature for each block from among the plurality of blocks in the image; processing the compressed features by an entropy encoder to generate a first compressed bitstream; obtaining a plurality of reshaped compressed features by concatenating the compressed features; processing the plurality of reshaped compressed features by the entropy encoder to generate a second compressed bitstream; and encoding the bitstream including the image based on the second compressed bitstream.

Block-wise entropy coding method in neural image compression

Disclosed herein are systems, methods and devices for controlling output of a storage device during read operations. The method comprises: measuring a length of a temporal gap between first and second consecutive read bursts from a storage device, the first and second read burst are in response to first and second read commands received by the storage device, respectively; generating a state code according to the length, wherein the state code has a first value when the length is zero, a second value when the length is equal to or shorter than a threshold time length but is non-zero, and a third value when the length is greater than the threshold time length; and controlling output of the storage device according to the state code.

Growing community of inventors

San Jose, CA, United States of America

Wei Jiang