公开(公告)号：US20240308505A1

公开(公告)日：2024-09-19

申请号：US18183867

申请日：2023-03-14

Applicant: QUALCOMM Incorporated

Inventor： Thomas Alexander RYDER ,  Muhammed Zeyd COBAN ,  Marta KARCZEWICZ

IPC: B60W30/095 ,  G06T7/215

CPC classification number: B60W30/0953 ,  G06T7/215

Abstract: A device includes one or more processors configured to obtain encoded data associated with one or more motion values. The one or more processors are also configured to obtain conditional input of a compression network, wherein the conditional input is based on one or more first predicted motion values. The one or more processors are further configured to process, using the compression network, the encoded data and the conditional input to generate one or more second predicted motion values.

公开(公告)号：US20240214578A1

公开(公告)日：2024-06-27

申请号：US18069974

申请日：2022-12-21

Applicant: QUALCOMM Incorporated

Inventor： Thomas Alexander RYDER ,  Muhammed Zeyd COBAN ,  Marta KARCZEWICZ

IPC: H04N19/147 ,  G06N3/08 ,  G06T9/00 ,  H04N19/124 ,  H04N19/172

CPC classification number: H04N19/147 ,  G06N3/08 ,  G06T9/002 ,  H04N19/124 ,  H04N19/172

Abstract: Systems and techniques are described for processing video data. For instance, a process can include processing a frame of video data using a first layer of a neural network-based video encoder, the neural network-based video encoder performing at least one quantization step. The process can further include applying an exponential-family prior to an output of the first layer of the neural network-based video encoder to generate a first layer output evaluation, generating a total loss value for the neural network-based video encoder based on a sum of a loss value for the neural network-based video encoder and the first layer output evaluation, and training the neural network-based video encoder based on the total loss value.