公开(公告)号：US20220279185A1

公开(公告)日：2022-09-01

申请号：US17187670

申请日：2021-02-26

Applicant: Lemon Inc.

Inventor： Weijia ZHU ,  Jizheng XU ,  Li ZHANG ,  Yue WANG

IPC: H04N19/13 ,  H04N19/176 ,  H04N19/169 ,  H04N19/132 ,  H04N19/105 ,  H04N19/82 ,  H04N19/117 ,  H04N19/186

Abstract: Example implementations include a method, apparatus and computer-readable medium of video coding, comprising determining, for a conversion between a video comprising a plurality of pictures and a bitstream of the video, first layer information which is utilized in a first process performed on a first layer of each picture. The implementations further include determining, second layer information which is utilized in a second process performed on a second layer of each picture. Additionally, the implementations further include performing the conversion for the second layer based on the first layer information and the second layer information.

公开(公告)号：US20220191483A1

公开(公告)日：2022-06-16

申请号：US17544638

申请日：2021-12-07

Applicant: Lemon Inc.

Inventor： Yue Li ,  Li Zhang ,  Kai Zhang

IPC: H04N19/117 ,  H04N19/436 ,  H04N19/82 ,  H04N19/186 ,  H04N19/169 ,  H04N19/70 ,  H04N19/124 ,  H04N19/176 ,  H04N19/132 ,  G06N3/08

Abstract: A method implemented by a video coding apparatus. The method includes selecting a neural network (NN) filter model from a plurality of NN filter model candidates for each video unit. The NN filter model selected for a first video unit is different than the NN filter model selected for a second video unit. The method also includes converting between a video media file and a bitstream based on the one or more NN filter models selected for the video unit. A corresponding video coding apparatus and non-transitory computer readable medium are also disclosed.

公开(公告)号：US20220132103A1

公开(公告)日：2022-04-28

申请号：US17512162

申请日：2021-10-27

Applicant: Lemon Inc.

Inventor： Yue Li ,  Li Zhang ,  Jizheng Xu

IPC: H04N19/105 ,  H04N19/119 ,  H04N19/96 ,  G06T9/00 ,  G06T9/40 ,  G06K9/00 ,  H04N19/176 ,  H04N19/159

Abstract: A method implemented by a coding apparatus. The method includes obtaining probabilities of split types being implemented when partitioning a picture, and skipping one or more of the split types based on the probabilities obtained when a coding block is partitioned during a conversion between a video media file and a bitstream. A corresponding apparatus and non-transitory computer readable medium are also provided.

公开(公告)号：US20220103781A1

公开(公告)日：2022-03-31

申请号：US17484919

申请日：2021-09-24

Applicant: Lemon Inc.

Inventor： Ye-Kui WANG

IPC: H04N7/01 ,  H04N19/172 ,  H04N19/70

Abstract: Systems, methods and apparatus for encoding, decoding or transcoding visual media data are described. One example method of processing visual media data includes performing a conversion between visual media data and a bitstream of the visual media data according to a format rule, wherein the format rule specifies that a supplemental enhancement information (SEI) message that refers to a dependent random access point (DRAP) picture is included in the bitstream, and wherein the format rule further specifies that the SEI message includes a syntax element indicating a number of intra random access point (IRAP) pictures or dependent random access point (DRAP) pictures that are within a same coded layer video sequence (CLVS) as the DRAP picture.

公开(公告)号：US20220101095A1

公开(公告)日：2022-03-31

申请号：US17487852

申请日：2021-09-28

Applicant: Lemon Inc.

Inventor： Yue LI ,  Li ZHANG ,  Kai ZHANG

IPC: G06N3/04 ,  H04N19/117 ,  H04N19/184 ,  H04N19/157

Abstract: Methods, systems, apparatus for media processing are described. One example method of digital media processing includes performing a conversion between visual media data and a bitstream of the visual media data, wherein the performing of the conversion includes selectively applying a convolutional neural network filter during the conversion based on a rule, and wherein the rule specifies whether and/or how the convolutional neural network filter is applied.

公开(公告)号：US20220086496A1

公开(公告)日：2022-03-17

申请号：US17473554

申请日：2021-09-13

Applicant: Lemon Inc.

Inventor： Ye-Kui WANG

IPC: H04N19/70 ,  H04N19/169 ,  H04N19/30

Abstract: Systems, methods and apparatus for generating or parsing a visual media file according to a file format include performing a conversion between a visual media data and a visual media file that stores a bitstream of the visual media data according to a format rule. The visual media file stores multiple tracks that belong to an entity group of a specific type. The format rule specifies that, responsive to the multiple tracks having a track reference to a particular type to a group identifier, the multiple tracks (A) omit carrying a sample group of a specific type or (B) carry the sample group of the specific type such that information in the sample group of the specific type is consistent with that in the entity group of the specific type.

公开(公告)号：US20220070496A1

公开(公告)日：2022-03-03

申请号：US17464311

申请日：2021-09-01

Applicant: Lemon Inc.

Inventor： Ye-Kui WANG ,  Li ZHANG

IPC: H04N19/70 ,  H04N19/172 ,  H04N19/593 ,  H04N19/30 ,  H04N19/169

Abstract: Systems, methods and apparatus for processing image data are described. One example method includes performing a conversion between a visual media file and a bitstream. The visual media file comprises image items each comprising a sequence of one or more pictures according to a media file format, and the bitstream comprises access units each comprising one or more pictures each belonging to a layer according to a video coding format. The video coding format defines multiple profiles. The media file format specifies that the bitstream is represented in a file having a specific brand, and that one or more profiles used for representing the video in the bitstream are agnostic of the specific brand.

公开(公告)号：US20220070495A1

公开(公告)日：2022-03-03

申请号：US17464364

申请日：2021-09-01

Applicant: Lemon Inc.

Inventor： Ye-Kui WANG ,  Li ZHANG

IPC: H04N19/67 ,  H04N19/159 ,  H04N19/107

Abstract: Systems, methods and apparatus for processing image data are described. One example method includes performing a conversion between a visual media file and a bitstream. The visual media file comprises a sequence of one or more pictures according to a media file format, and the bitstream comprises one or more access units according to a video coding format. The bitstream is coded according to the video coding format. The media file format specifies that an image item of a specific type value in the visual media file includes a single access unit of the bitstream. The single access unit is either an Intra Random Access Picture (IRAP) access unit or a Gradual Decoding Refresh (GDR) access unit according to the video coding format. All pictures in the GDR access unit are identified as a recovery point in the bitstream.

公开(公告)号：US20250166267A1

公开(公告)日：2025-05-22

申请号：US18949486

申请日：2024-11-15

Applicant: Lemon Inc.

Inventor： Song BAI ,  Yujun Shi ,  Chuhui Xue ,  Wenqing Zhang

IPC: G06T11/60 ,  G06V10/48

Abstract: Embodiments of the disclosure relate to interactive point-based image editing. According to example embodiments of the present disclosure, a user edit input for a source image is obtained to indicate at least one handle point and at least one target point in the source image. A feature map is extracted from the source image using a diffusion model at an iteration step of an inverse denoising diffusion process performed on the source image. The feature map is then updated based on the user edit input. Then a target image is generated based on the updated feature map using the diffusion model through a denoising diffusion process performed on the updated feature map.

公开(公告)号：US20250165273A1

公开(公告)日：2025-05-22

申请号：US18949558

申请日：2024-11-15

Applicant: Beijing Zitiao Network Technology Co., Ltd. ,  Lemon Inc.

Inventor： Lingyu WANG ,  Koken ISHII ,  Xin ZHONG ,  Yingdi SUN

IPC: G06F9/451 ,  G06F3/0481 ,  G06F3/04842

Abstract: A method, an apparatus, a device and a storage medium are provided. In the method, in response to a predetermined operation associated with a conversation window of a user and a digital assistant, a first message from the digital assistant is presented in the conversation window. In the method, in the first message, an element related to one or more task components is presented. Each task component is configured to perform a corresponding function. The task component includes at least one of a plug-in or a scenario.