公开(公告)号：US20250168369A1

公开(公告)日：2025-05-22

申请号：US19033120

申请日：2025-01-21

Applicant: Bytedance Inc.

Inventor： Semih Esenlik ,  Zhaobin Zhang ,  Kai Zhang ,  Li Zhang

IPC: H04N19/192 ,  H04N19/124 ,  H04N19/159 ,  H04N19/184

Abstract: A mechanism for processing video data is in a neural network disclosed. The mechanism includes obtaining quantized residual latent samples. The quantized residual latent samples are processed to obtain processed quantized residual latent samples. A reconstructed latent sample can then be acquired based on the processed quantized residual latent sample.

公开(公告)号：US20250159258A1

公开(公告)日：2025-05-15

申请号：US19022954

申请日：2025-01-15

Applicant: Douyin Vision (Beijing) Co., Ltd. ,  Bytedance Inc.

Inventor： Semih Esenlik ,  Zhaobin Zhang ,  Yaojun Wu ,  Yue Li ,  Kai Zhang ,  Li Zhang

IPC: H04N19/625 ,  H04N19/124 ,  H04N19/63

Abstract: Embodiments of the present disclosure provide a solution for visual data processing. A method for visual data processing is proposed. The method comprises: obtaining, for a conversion between visual data and a bitstream of the visual data, region information indicating positions and sizes of a plurality of regions in a quantized latent representation of the visual data; selecting, based on the region information, a set of target neighboring samples from a plurality of candidate neighboring samples of a current sample in the quantized latent representation, the set of target neighboring samples being in the same region as the current sample; determining statistical information of the current sample based on the set of target neighboring samples; and performing the conversion based on the statistical information.

公开(公告)号：US20250030857A1

公开(公告)日：2025-01-23

申请号：US18828890

申请日：2024-09-09

Applicant: Beijing Bytedance Network Technology Co., Ltd. ,  Bytedance Inc.

Inventor： Yaojun Wu ,  Semih Esenlik ,  Zhaobin Zhang ,  Yue Li ,  Kai Zhang ,  Li Zhang

IPC: H04N19/126 ,  H04N19/42

Abstract: Embodiments of the present disclosure provide a solution for visual data processing. A method for visual data processing is proposed. The method comprises: performing, for a conversion between visual data and a bitstream of the visual data, a quantization process on a dataset comprising at least one of: input visual data of a neural network model used for the conversion, or a parameter of the neural network model; and performing the conversion based on the quantization process.

公开(公告)号：US20250168370A1

公开(公告)日：2025-05-22

申请号：US19033178

申请日：2025-01-21

Applicant: Bytedance Inc.

Inventor： Semih Esenlik ,  Zhaobin Zhang ,  Kai Zhang ,  Li Zhang

IPC: H04N19/192 ,  H04N19/124 ,  H04N19/70

Abstract: An image decoding method including transforming an input image into latent samples using an analysis transform; quantizing the latent samples using a hyper encoder to generate quantized hyper latent samples; encoding the quantized hyper latent samples into a bitstream using entropy encoding; applying a latent sample prediction process to obtain quantized latent samples and quantized residual latent samples based on the latent samples using the quantized hyper latent samples; obtaining prediction samples following the latent sample prediction process; and entropy encoding the quantized hyper latent samples and the quantized residual latent samples into the bitstream.

公开(公告)号：US20250159214A1

公开(公告)日：2025-05-15

申请号：US19021539

申请日：2025-01-15

Applicant: Bytedance Inc.

Inventor： Zhaobin Zhang ,  Semih Esenlik ,  Kai Zhang ,  Li Zhang

IPC: H04N19/189 ,  H04N19/119 ,  H04N19/176

Abstract: An image decoding method including obtaining reconstructed latents ŷ[:,:,:] using an arithmetic decoder; feeding the reconstructed latents into a synthesis neural network; tile partitioning output feature maps into multiple parts based on decoded parameters at one or multiple locations; separately feeding each of the multiple parts into a next stage of a plurality of convolutional layers to obtain spatially partitioned feature maps at an output; and cropping and stitching the spatially partitioned feature maps back to a whole feature map spatially until an image is reconstructed.

公开(公告)号：US20250119552A1

公开(公告)日：2025-04-10

申请号：US18982647

申请日：2024-12-16

Applicant: Douyin Vision (Beijing) Co., Ltd. ,  Bytedance Inc.

Inventor： Zhaobin Zhang ,  Semih Esenlik ,  Yaojun Wu ,  Yue Li ,  Kai Zhang ,  Li Zhang

IPC: H04N19/149 ,  H04N19/122 ,  H04N19/186

Abstract: A mechanism for processing video data is disclosed. A determination is made to resize an image with a first size to create a resized image with a second size. A conversion is performed between a visual media data and a bitstream based on the resized image. The conversion includes applying a neural network-based coding model to the resized image to achieve variable rate neural network-based compression.

公开(公告)号：US20240414381A1

公开(公告)日：2024-12-12

申请号：US18807764

申请日：2024-08-16

Applicant: Beijing Bytedance Network Technology Co., Ltd. ,  Bytedance Inc.

Inventor： Yaojun WU ,  Yue Li ,  Zhaobin Zhang ,  Semih Esenlik ,  Kai Zhang ,  Li Zhang

IPC: H04N19/91 ,  H04N7/01 ,  H04N19/60

Abstract: Embodiments of the present disclosure provide a solution for data processing. A method for data processing is proposed. The method comprises: determining, by using a first model with an attention mechanism during a conversion between data and a bitstream of the data, a probability distribution for entropy coding associated with the bitstream; and performing the conversion based on the probability distribution.