公开(公告)号：US20220366546A1

公开(公告)日：2022-11-17

申请号：US17812639

申请日：2022-07-14

Applicant: ADOBE INC.

Inventor： Zhe LIN ,  Yu ZENG ,  Jimei YANG ,  Jianming ZHANG ,  Elya SHECHTMAN

IPC: G06T5/00 ,  G06N3/04 ,  G06N3/08

Abstract: Methods and systems are provided for accurately filling holes, regions, and/or portions of images using iterative image inpainting. In particular, iterative inpainting utilize a confidence analysis of predicted pixels determined during the iterations of inpainting. For instance, a confidence analysis can provide information that can be used as feedback to progressively fill undefined pixels that comprise the holes, regions, and/or portions of an image where information for those respective pixels is not known. To allow for accurate image inpainting, one or more neural networks can be used. For instance, a coarse result neural network (e.g., a GAN comprised of a generator and a discriminator) and a fine result neural network (e.g., a GAN comprised of a generator and two discriminators). The image inpainting system can use such networks to predict an inpainting image result that fills the hole, region, and/or portion of the image using predicted pixels and generates a corresponding confidence map of the predicted pixels.

公开(公告)号：US20210342984A1

公开(公告)日：2021-11-04

申请号：US16864388

申请日：2020-05-01

Applicant: ADOBE INC.

Inventor： Zhe LIN ,  Yu ZENG ,  Jimei YANG ,  Jianming ZHANG ,  Elya SHECHTMAN

IPC: G06T5/00 ,  G06T3/40

Abstract: Methods and systems are provided for accurately filling holes, regions, and/or portions of high-resolution images using guided upsampling during image inpainting. For instance, an image inpainting system can apply guided upsampling to an inpainted image result to enable generation of a high-resolution inpainting result from a lower-resolution image that has undergone inpainting. To allow for guided upsampling during image inpainting, one or more neural networks can be used. For instance, a low-resolution result neural network (e.g., comprised of an encoder and a decoder) and a high-resolution input neural network (e.g., comprised of an encoder and a decoder). The image inpainting system can use such networks to generate a high-resolution inpainting image result that fills the hole, region, and/or portion of the image.

公开(公告)号：US20210342983A1

公开(公告)日：2021-11-04

申请号：US16861548

申请日：2020-04-29

Applicant: ADOBE INC.

Inventor： Zhe LIN ,  Yu ZENG ,  Jimei YANG ,  Jianming ZHANG ,  Elya SHECHTMAN

IPC: G06T5/00 ,  G06N3/04 ,  G06N3/08

Abstract: Methods and systems are provided for accurately filling holes, regions, and/or portions of images using iterative image inpainting. In particular, iterative inpainting utilize a confidence analysis of predicted pixels determined during the iterations of inpainting. For instance, a confidence analysis can provide information that can be used as feedback to progressively fill undefined pixels that comprise the holes, regions, and/or portions of an image where information for those respective pixels is not known. To allow for accurate image inpainting, one or more neural networks can be used. For instance, a coarse result neural network (e.g., a GAN comprised of a generator and a discriminator) and a fine result neural network (e.g., a GAN comprised of a generator and two discriminators). The image inpainting system can use such networks to predict an inpainting image result that fills the hole, region, and/or portion of the image using predicted pixels and generates a corresponding confidence map of the predicted pixels.