公开(公告)号：US12277671B2

公开(公告)日：2025-04-15

申请号：US17454434

申请日：2021-11-10

Applicant: ADOBE INC.

Inventor： Shouchang Guo ,  Arthur Jules Martin Roullier ,  Tamy Boubekeur ,  Valentin Deschaintre ,  Jerome Derel ,  Paul Parneix

IPC: G06T3/4046 ,  G06T5/77 ,  G06T7/11 ,  G06T7/40

Abstract: Systems and methods for image processing are described. Embodiments of the present disclosure include an image processing apparatus configured to efficiently perform texture synthesis (e.g., increase the size of, or extend, texture in an input image while preserving a natural appearance of the synthesized texture pattern in the modified output image). In some aspects, the image processing apparatus implements an attention mechanism with a multi-stage attention model where different stages (e.g., different transformer blocks) progressively refine image feature patch mapping at different scales, while utilizing repetitive patterns in texture images to enable network generalization. One or more embodiments of the disclosure include skip connections and convolutional layers (e.g., between transformer block stages) that combine high-frequency and low-frequency features from different transformer stages and unify attention to micro-structures, meso-structures and macro-structures. In some aspects, the skip connections enable information propagation in the transformer network.

公开(公告)号：US20230144637A1

公开(公告)日：2023-05-11

申请号：US17454434

申请日：2021-11-10

Applicant: ADOBE INC.

Inventor： Shouchang Guo ,  Arthur Jules Martin ROULLIER ,  Tamy Boubekeur ,  Valentin Deschaintre ,  Jerome Derel ,  Paul Parneix

IPC: G06T3/40 ,  G06T5/00 ,  G06T7/11 ,  G06T7/40

CPC classification number: G06T3/4046 ,  G06T5/005 ,  G06T7/11 ,  G06T7/40

Abstract: Systems and methods for image processing are described. Embodiments of the present disclosure include an image processing apparatus configured to efficiently perform texture synthesis (e.g., increase the size of, or extend, texture in an input image while preserving a natural appearance of the synthesized texture pattern in the modified output image). In some aspects, the image processing apparatus implements an attention mechanism with a multi-stage attention model where different stages (e.g., different transformer blocks) progressively refine image feature patch mapping at different scales, while utilizing repetitive patterns in texture images to enable network generalization. One or more embodiments of the disclosure include skip connections and convolutional layers (e.g., between transformer block stages) that combine high-frequency and low-frequency features from different transformer stages and unify attention to micro-structures, meso-structures and macro-structures. In some aspects, the skip connections enable information propagation in the transformer network.