公开(公告)号：US20240371007A1

公开(公告)日：2024-11-07

申请号：US18770386

申请日：2024-07-11

Applicant: Adobe Inc.

Inventor： Zhe LIN ,  Simon Su Chen ,  Jason wen-young Kuen ,  Bo Sun

IPC: G06T7/194 ,  G06N3/08 ,  G06T7/11

Abstract: Various disclosed embodiments are directed to refining or correcting individual semantic segmentation/instance segmentation masks that have already been produced by baseline models in order to generate a final coherent panoptic segmentation map. Specifically, a refinement model, such as an encoder-decoder-based neural network, generates or predicts various data objects, such as foreground masks, bounding box offset maps, center maps, center offset maps, and coordinate convolution. This, among other functionality described herein, improves the inaccuracies and computing resource consumption of existing technologies.

公开(公告)号：US20230154185A1

公开(公告)日：2023-05-18

申请号：US17454740

申请日：2021-11-12

Applicant: ADOBE INC.

Inventor： Jason Wen Yong Kuen ,  Bo Sun ,  Zhe Lin ,  Simon Su Chen

IPC: G06K9/00 ,  G06K9/62 ,  G06T3/40 ,  G06T9/00 ,  G06N3/08

CPC classification number: G06K9/00624 ,  G06K9/6202 ,  G06K9/6261 ,  G06N3/08 ,  G06T3/4046 ,  G06T9/002

Abstract: Systems and methods for image processing are described. Embodiments of the present disclosure receive an image having a plurality of object instances; encode the image to obtain image features; decode the image features to obtain object features; generate object detection information based on the object features using an object detection branch, wherein the object detection branch is trained based on a first training set using a detection loss; generate semantic segmentation information based on the object features using a semantic segmentation branch, wherein the semantic segmentation branch is trained based on a second training set different from the first training set using a semantic segmentation loss; and combine the object detection information and the semantic segmentation information to obtain panoptic segmentation information that indicates which pixels of the image correspond to each of the plurality of object instances.

公开(公告)号：US11941884B2

公开(公告)日：2024-03-26

申请号：US17454740

申请日：2021-11-12

Applicant: ADOBE INC.

Inventor： Jason Wen Yong Kuen ,  Bo Sun ,  Zhe Lin ,  Simon Su Chen

IPC: G06K9/00 ,  G06F18/21 ,  G06N3/08 ,  G06T9/00 ,  G06V10/75 ,  G06V20/40

CPC classification number: G06V20/41 ,  G06F18/2163 ,  G06N3/08 ,  G06T3/4046 ,  G06T9/002 ,  G06V10/751

Abstract: Systems and methods for image processing are described. Embodiments of the present disclosure receive an image having a plurality of object instances; encode the image to obtain image features; decode the image features to obtain object features; generate object detection information based on the object features using an object detection branch, wherein the object detection branch is trained based on a first training set using a detection loss; generate semantic segmentation information based on the object features using a semantic segmentation branch, wherein the semantic segmentation branch is trained based on a second training set different from the first training set using a semantic segmentation loss; and combine the object detection information and the semantic segmentation information to obtain panoptic segmentation information that indicates which pixels of the image correspond to each of the plurality of object instances.

公开(公告)号：US12067730B2

公开(公告)日：2024-08-20

申请号：US17495618

申请日：2021-10-06

Applicant: ADOBE INC.

Inventor： Zhe Lin ,  Simon Su Chen ,  Jason Wen-youg Kuen ,  Bo Sun

IPC: G06K9/00 ,  G06N3/08 ,  G06T7/11 ,  G06T7/194

CPC classification number: G06T7/194 ,  G06N3/08 ,  G06T7/11

Abstract: Various disclosed embodiments are directed to refining or correcting individual semantic segmentation/instance segmentation masks that have already been produced by baseline models in order to generate a final coherent panoptic segmentation map. Specifically, a refinement model, such as an encoder-decoder-based neural network, generates or predicts various data objects, such as foreground masks, bounding box offset maps, center maps, center offset maps, and coordinate convolution. This, among other functionality described herein, improves the inaccuracies and computing resource consumption of existing technologies.

公开(公告)号：US20240046567A1

公开(公告)日：2024-02-08

申请号：US17817776

申请日：2022-08-05

Applicant: Adobe Inc.

Inventor： Siddhartha Chaudhuri ,  Bo Sun ,  Vladimir Kim ,  Noam Aigerman

IPC: G06T17/20 ,  G06V10/22 ,  G06V10/75

CPC classification number: G06T17/20 ,  G06V10/22 ,  G06V10/754 ,  G06V2201/12

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed that utilizes machine learning models for patch retrieval and deformation in completing three-dimensional digital shapes. In particular, in one or more implementations the disclosed systems utilize a machine learning model to predict a coarse completion shape from an incomplete 3D digital shape. The disclosed systems sample coarse 3D patches from the coarse 3D digital shape and learn a shape distance function to retrieve detailed 3D shape patches in the input shape. Moreover, the disclosed systems learn a deformation for each retrieved patch and blending weights to integrate the retrieved patches into a continuous surface.