Techniques for image attribute editing using neural networks

    公开(公告)号:US11967049B2

    公开(公告)日:2024-04-23

    申请号:US17531640

    申请日:2021-11-19

    Applicant: Adobe Inc.

    CPC classification number: G06T5/005 G06N3/045 G06V10/7553

    Abstract: The present disclosure describes multi-stage image editing techniques to improve detail and accuracy in edited images. An input image including a target region to be edited and an edit parameter specifying a modification to the target region are received. A parsing map of the input image is generated. A latent representation of the parsing map is generated. An edit is applied to the latent representation of the parsing map based on the edit parameter. The edited latent representation is input to a neural network to generate a modified parsing map including the target region with a shape change according to the edit parameter. Based on the input image and the modified parsing map, a masked image corresponding to the shape change is generated. Based on the masked image, a neural network is used to generate an edited image with the modification to the target region.

    TECHNIQUES FOR IMAGE ATTRIBUTE EDITING USING NEURAL NETWORKS

    公开(公告)号:US20230162330A1

    公开(公告)日:2023-05-25

    申请号:US17531640

    申请日:2021-11-19

    Applicant: Adobe Inc.

    CPC classification number: G06T5/005 G06N3/0454 G06K9/6209

    Abstract: The present disclosure describes multi-stage image editing techniques to improve detail and accuracy in edited images. An input image including a target region to be edited and an edit parameter specifying a modification to the target region are received. A parsing map of the input image is generated. A latent representation of the parsing map is generated. An edit is applied to the latent representation of the parsing map based on the edit parameter. The edited latent representation is input to a neural network to generate a modified parsing map including the target region with a shape change according to the edit parameter. Based on the input image and the modified parsing map, a masked image corresponding to the shape change is generated. Based on the masked image, a neural network is used to generate an edited image with the modification to the target region.

    View synthesis with spatial and rotational consistency

    公开(公告)号:US12051175B2

    公开(公告)日:2024-07-30

    申请号:US17097600

    申请日:2020-11-13

    Applicant: ADOBE INC.

    Abstract: Methods, system, and computer storage media are provided for novel view synthesis. An input image depicting an object is received and utilized to generate, via a neural network, a target view image. In exemplary aspects, additional view images are also generated within the same pass of the neural network. A loss is determined based on the target view image and additional view images and is used to modify the neural network to reduce errors. In some aspects, a rotated view image is generated by warping a ground truth image from an initial angle to a rotated view angle that matches a view angle of an image synthesized via the neural network, such as a target view image. The rotated view image and the synthesized image matching the rotated view angle (e.g., a target view image) are utilized to compute a rotational loss.

    NOVEL VIEW SYNTHESIS WITH SPATIAL AND ROTATIONAL CONSISTENCY

    公开(公告)号:US20220156886A1

    公开(公告)日:2022-05-19

    申请号:US17097600

    申请日:2020-11-13

    Applicant: ADOBE INC.

    Abstract: Methods, system, and computer storage media are provided for novel view synthesis. An input image depicting an object is received and utilized to generate, via a neural network, a target view image. In exemplary aspects, additional view images are also generated within the same pass of the neural network. A loss is determined based on the target view image and additional view images and is used to modify the neural network to reduce errors. In some aspects, a rotated view image is generated by warping a ground truth image from an initial angle to a rotated view angle that matches a view angle of an image synthesized via the neural network, such as a target view image. The rotated view image and the synthesized image matching the rotated view angle (e.g., a target view image) are utilized to compute a rotational loss.

Patent Agency Ranking