公开(公告)号：US20240214591A1

公开(公告)日：2024-06-27

申请号：US18455982

申请日：2023-08-25

Applicant: Tencent America LLC

Inventor： Yang SUI ,  Ding Ding ,  Xiaozhong Xu ,  Shan Liu

IPC: H04N19/42 ,  H04N19/119 ,  H04N19/136 ,  H04N19/60

CPC classification number: H04N19/42 ,  H04N19/119 ,  H04N19/136 ,  H04N19/60

Abstract: Methods and apparatuses for neural network based image compression may be provided. The method may include generating a feature map comprising a plurality of channels for a compressed image; splitting the generated feature map into a first number of split feature maps; and reconstructing the compressed image using one or more long-range attention models with one or more variable receptive fields associated with a respective split feature map.

公开(公告)号：US20240214592A1

公开(公告)日：2024-06-27

申请号：US18458507

申请日：2023-08-30

Applicant: Tencent America LLC

Inventor： Yang SUI ,  Ding DING ,  Xiaozhong XU ,  Shan LIU

IPC: H04N19/42 ,  H04N19/119 ,  H04N19/167 ,  H04N19/176

CPC classification number: H04N19/42 ,  H04N19/119 ,  H04N19/167 ,  H04N19/176

Abstract: Methods and apparatuses for decoding a compressed image using a neural image compression network may be provided. The method may include generating long-range context model parameters associated with a high resolution compressed image, the long-range context model parameters corresponding to a first area. The method may also include splitting the generated long-range context model parameters into a first number of context parameter blocks. The method may also include for each block in the first number of context parameter blocks, predicting respective context features using a long-range context model and respective context parameter blocks, wherein the long-range context model uses a corner-to-center latent decoding strategy or an edge-to-center latent decoding strategy to decode latents associated with the high resolution compressed image. Then, the high resolution compressed image may be reconstructed based on predicted context features.

公开(公告)号：US20240212215A1

公开(公告)日：2024-06-27

申请号：US18458595

申请日：2023-08-30

Applicant: Tencent America LLC

Inventor： Yang SUI ,  Ding DING ,  Xiaozhong XU ,  Shan LIU

IPC: G06T9/00 ,  G06T7/13 ,  G06V10/44

CPC classification number: G06T9/00 ,  G06T7/13 ,  G06V10/44 ,  G06T2207/20164

Abstract: Methods and apparatuses for decoding a compressed image using a neural image compression network are provided. The method may include generating context parameters associated with a compressed image, the context parameters corresponding to a first area. The method may also include determining that a long range global dependency exists between a first latent and a second latent in a long-range global area within the compressed image and predicting a plurality of context features using a transformer-based long-range context prediction model. The method may then include reconstructing the compressed image based on the predicted plurality of context features.