公开(公告)号：US11924445B2

公开(公告)日：2024-03-05

申请号：US17201944

申请日：2021-03-15

申请人： QUALCOMM Incorporated

发明人： Ties Jehan Van Rozendaal ,  Iris Anne Marie Huijben ,  Taco Sebastiaan Cohen

IPC分类号： H04N19/184 ,  G06N3/045 ,  G06N3/088

CPC分类号： H04N19/184 ,  G06N3/045 ,  G06N3/088

摘要： Techniques are described for compressing data using machine learning systems and tuning machine learning systems for compressing the data. An example process can include receiving, by a neural network compression system (e.g., trained on a training dataset), input data for compression by the neural network compression system. The process can include determining a set of updates for the neural network compression system, the set of updates including updated model parameters tuned using the input data. The process can include generating, by the neural network compression system using a latent prior, a first bitstream including a compressed version of the input data. The process can further include generating, by the neural network compression system using the latent prior and a model prior, a second bitstream including a compressed version of the updated model parameters. The process can include outputting the first bitstream and the second bitstream for transmission to a receiver.

公开(公告)号：US11405626B2

公开(公告)日：2022-08-02

申请号：US17091570

申请日：2020-11-06

申请人： QUALCOMM Incorporated

发明人： Adam Waldemar Golinski ,  Yang Yang ,  Reza Pourreza ,  Guillaume Konrad Sautiere ,  Ties Jehan Van Rozendaal ,  Taco Sebastiaan Cohen

IPC分类号： H04N19/42 ,  H04N19/137 ,  G06N3/08 ,  H04N19/85 ,  H04N19/172

摘要： Techniques are described herein for coding video content using recurrent-based machine learning tools. A device can include a neural network system including encoder and decoder portions. The encoder portion can generate output data for the current time step of operation of the neural network system based on an input video frame for a current time step of operation of the neural network system, reconstructed motion estimation data from a previous time step of operation, reconstructed residual data from the previous time step of operation, and recurrent state data from at least one recurrent layer of a decoder portion of the neural network system from the previous time step of operation. A decoder portion of the neural network system can generate, based on the output data and recurrent state data from the previous time step of operation, a reconstructed video frame for the current time step of operation.

公开(公告)号：US20240305785A1

公开(公告)日：2024-09-12

申请号：US18457079

申请日：2023-08-28

申请人： QUALCOMM Incorporated

发明人： Ties Jehan Van Rozendaal ,  Hoang Cong Minh Le ,  Tushar Singhal ,  Amir Said ,  Krishna Buska ,  Guillaume Konrad Sautiere ,  Anjuman Raha ,  Auke Joris Wiggers ,  Frank Steven Mayer ,  Liang Zhang ,  Abhijit Khobare ,  Muralidhar Reddy Akula

IPC分类号： H04N19/137 ,  H04N19/159 ,  H04N19/176 ,  H04N19/192

CPC分类号： H04N19/137 ,  H04N19/159 ,  H04N19/176 ,  H04N19/192

摘要： An example computing device may include memory and one or more processors. The one or more processors may be configured to parallel entropy decode encoded video data from a received bitstream to generate entropy decoded data. The one or more processors may be configured to predict a motion vector based on the entropy decoded data. The one or more processors may be configured to decode a motion vector residual from the entropy decoded data. The one or more processors may be configured to add the motion vector residual and motion vector. The one or more processors may be configured to warp previous reconstructed video data with an overlapped block-based warp function using the motion vector to generate predicted current video data. The one or more processors may be configured to sum the predicted current video data with a residual block to generate current reconstructed video data.

公开(公告)号：US11729406B2

公开(公告)日：2023-08-15

申请号：US16826221

申请日：2020-03-21

申请人： QUALCOMM Incorporated

发明人： Amirhossein Habibian ,  Ties Jehan Van Rozendaal ,  Taco Sebastiaan Cohen

IPC分类号： H04N19/14 ,  H04N19/124 ,  H04N19/179 ,  H04N19/186 ,  H04N19/46 ,  H04N5/247 ,  G06K9/00 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  H04N19/20 ,  G06N3/084 ,  G06V20/40 ,  G06F18/21 ,  G06N3/044 ,  G06N3/045 ,  G06N3/047 ,  H04N23/90 ,  G06V10/764 ,  G06V10/82

CPC分类号： H04N19/20 ,  G06F18/21 ,  G06N3/044 ,  G06N3/045 ,  G06N3/047 ,  G06N3/084 ,  G06V10/764 ,  G06V10/82 ,  G06V20/46 ,  H04N19/124 ,  H04N19/14 ,  H04N19/179 ,  H04N19/186 ,  H04N19/46 ,  H04N23/90

摘要： Certain aspects of the present disclosure are directed to methods and apparatus for compressing video content using deep generative models. One example method generally includes receiving video content for compression. The received video content is generally encoded into a latent code space through an encoder, which may be implemented by a first artificial neural network. A compressed version of the encoded video content is generally generated through a trained probabilistic model, which may be implemented by a second artificial neural network, and output for transmission.