公开(公告)号：US20230169632A1

公开(公告)日：2023-06-01

申请号：US17521503

申请日：2021-11-08

申请人： Adobe Inc.

发明人： Kuldeep Kulkarni ,  Soumya Dash ,  Hrituraj Singh ,  Bholeshwar Khurana ,  Aniruddha Mahapatra ,  Abhishek Bhatia

IPC分类号： G06T5/50 ,  G06T7/181

CPC分类号： G06T5/50 ,  G06T7/181

摘要： Certain aspects and features of this disclosure relate to semantically-aware image extrapolation. In one example, an input image is segmented to produce an input segmentation map of object instances in the input image. An object generation network is used to generate an extrapolated semantic label map for an extrapolated image. The extrapolated semantic label map includes instances in the original image and instances that will appear in an outpainted region of the extrapolated image. A panoptic label map is derived from coordinates of output instances in the extrapolated image and used to identify partial instances and boundaries. Instance-aware context normalization is used to apply one or more characteristics from the input image to the outpainted region to maintain semantic continuity. The extrapolated image includes the original image and the outpainted region and can be rendered or stored for future use.

公开(公告)号：US20240331102A1

公开(公告)日：2024-10-03

申请号：US18737344

申请日：2024-06-07

申请人： Adobe Inc.

发明人： Kuldeep Kulkarni ,  Soumya Dash ,  Hrituraj Singh ,  Bholeshwar Khurana ,  Aniruddha Mahapatra ,  Abhishek Bhatia

IPC分类号： G06T5/50 ,  G06N3/045 ,  G06T7/11 ,  G06T7/181 ,  G06V10/26 ,  G06V10/82 ,  G06V20/70

CPC分类号： G06T5/50 ,  G06T7/181 ,  G06V20/70 ,  G06N3/045 ,  G06T7/11 ,  G06V10/26 ,  G06V10/82

摘要： Certain aspects and features of this disclosure relate to semantically-aware image extrapolation. In one example, an input image is segmented to produce an input segmentation map of object instances in the input image. An object generation network is used to generate an extrapolated semantic label map for an extrapolated image. The extrapolated semantic label map includes instances in the original image and instances that will appear in an outpainted region of the extrapolated image. A panoptic label map is derived from coordinates of output instances in the extrapolated image and used to identify partial instances and boundaries. Instance-aware context normalization is used to apply one or more characteristics from the input image to the outpainted region to maintain semantic continuity. The extrapolated image includes the original image and the outpainted region and can be rendered or stored for future use.

公开(公告)号：US12020403B2

公开(公告)日：2024-06-25

申请号：US17521503

申请日：2021-11-08

申请人： Adobe Inc.

发明人： Kuldeep Kulkarni ,  Soumya Dash ,  Hrituraj Singh ,  Bholeshwar Khurana ,  Aniruddha Mahapatra ,  Abhishek Bhatia

IPC分类号： G06T5/50 ,  G06T7/181 ,  G06V20/70 ,  G06N3/045 ,  G06T7/11 ,  G06V10/26 ,  G06V10/82

CPC分类号： G06T5/50 ,  G06T7/181 ,  G06V20/70 ,  G06N3/045 ,  G06T7/11 ,  G06V10/26 ,  G06V10/82

摘要： Certain aspects and features of this disclosure relate to semantically-aware image extrapolation. In one example, an input image is segmented to produce an input segmentation map of object instances in the input image. An object generation network is used to generate an extrapolated semantic label map for an extrapolated image. The extrapolated semantic label map includes instances in the original image and instances that will appear in an outpainted region of the extrapolated image. A panoptic label map is derived from coordinates of output instances in the extrapolated image and used to identify partial instances and boundaries. Instance-aware context normalization is used to apply one or more characteristics from the input image to the outpainted region to maintain semantic continuity. The extrapolated image includes the original image and the outpainted region and can be rendered or stored for future use.