公开(公告)号：US20230259778A1

公开(公告)日：2023-08-17

申请号：US18309367

申请日：2023-04-28

Applicant: Adobe Inc.

Inventor： Shikun Liu ,  Zhe Lin ,  Yilin Wang ,  Jianming Zhang ,  Federico Perazzi

IPC: G06N3/082 ,  G06N3/04

CPC classification number: G06N3/082 ,  G06N3/04

Abstract: The disclosure describes one or more implementations of a neural network architecture pruning system that automatically and progressively prunes neural networks. For instance, the neural network architecture pruning system can automatically reduce the size of an untrained or previously-trained neural network without reducing the accuracy of the neural network. For example, the neural network architecture pruning system jointly trains portions of a neural network while progressively pruning redundant subsets of the neural network at each training iteration. In many instances, the neural network architecture pruning system increases the accuracy of the neural network by progressively removing excess or redundant portions (e.g., channels or layers) of the neural network. Further, by removing portions of a neural network, the neural network architecture pruning system can increase the efficiency of the neural network.

公开(公告)号：US20230206462A1

公开(公告)日：2023-06-29

申请号：US18175481

申请日：2023-02-27

Applicant: Adobe Inc.

Inventor： Qihang Yu ,  Jianming Zhang ,  He Zhang ,  Yilin Wang ,  Zhe Lin ,  Ning Xu

IPC: G06T7/194 ,  G06T7/136 ,  G06T7/11 ,  G06T3/40 ,  G06T5/00

CPC classification number: G06T7/194 ,  G06T7/136 ,  G06T7/11 ,  G06T3/4053 ,  G06T3/4046 ,  G06T5/009 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods that utilize a progressive refinement network to refine alpha mattes generated utilizing a mask-guided matting neural network. In particular, the disclosed systems can use the matting neural network to process a digital image and a coarse guidance mask to generate alpha mattes at discrete neural network layers. In turn, the disclosed systems can use the progressive refinement network to combine alpha mattes and refine areas of uncertainty. For example, the progressive refinement network can combine a core alpha matte corresponding to more certain core regions of a first alpha matte and a boundary alpha matte corresponding to uncertain boundary regions of a second, higher resolution alpha matte. Based on the combination of the core alpha matte and the boundary alpha matte, the disclosed systems can generate a final alpha matte for use in image matting processes.

公开(公告)号：US11507777B2

公开(公告)日：2022-11-22

申请号：US15930539

申请日：2020-05-13

Applicant: Adobe Inc.

Inventor： Sohrab Amirghodsi ,  Zhe Lin ,  Yilin Wang ,  Tianshu Yu ,  Connelly Barnes ,  Elya Shechtman

IPC: G06K9/62 ,  G06V10/75 ,  G06F17/18 ,  G06N3/08 ,  G06N20/00

Abstract: A panoptic labeling system includes a modified panoptic labeling neural network (“modified PLNN”) that is trained to generate labels for pixels in an input image. The panoptic labeling system generates modified training images by combining training images with mask instances from annotated images. The modified PLNN determines a set of labels representing categories of objects depicted in the modified training images. The modified PLNN also determines a subset of the labels representing categories of objects depicted in the input image. For each mask pixel in a modified training image, the modified PLNN calculates a probability indicating whether the mask pixel has the same label as an object pixel. The modified PLNN generates a mask label for each mask pixel, based on the probability. The panoptic labeling system provides the mask label to, for example, a digital graphics editing system that uses the labels to complete an infill operation.

公开(公告)号：US20220292684A1

公开(公告)日：2022-09-15

申请号：US17200525

申请日：2021-03-12

Applicant: Adobe Inc.

Inventor： Yilin Wang ,  Chenglin Yang ,  Jianming Zhang ,  He Zhang ,  Zhe Lin

IPC: G06T7/11 ,  G06K9/62 ,  G06T3/40 ,  G06N3/04 ,  G06N3/08

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that utilizes a neural network having a hierarchy of hierarchical point-wise refining blocks to generate refined segmentation masks for high-resolution digital visual media items. For example, in one or more embodiments, the disclosed systems utilize a segmentation refinement neural network having an encoder and a recursive decoder to generate the refined segmentation masks. The recursive decoder includes a deconvolution branch for generating feature maps and a refinement branch for generating and refining segmentation masks. In particular, in some cases, the refinement branch includes a hierarchy of hierarchical point-wise refining blocks that recursively refine a segmentation mask generated for a digital visual media item. In some cases, the disclosed systems utilize a segmentation refinement neural network that includes a low-resolution network and a high-resolution network, each including an encoder and a recursive decoder, to generate the refined segmentation masks.

公开(公告)号：US20220262009A1

公开(公告)日：2022-08-18

申请号：US17177595

申请日：2021-02-17

Applicant: Adobe Inc.

Inventor： Qihang Yu ,  Jianming Zhang ,  He Zhang ,  Yilin Wang ,  Zhe Lin ,  Ning Xu

IPC: G06T7/194 ,  G06T7/136 ,  G06T7/11 ,  G06T5/00 ,  G06T3/40

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods that utilize a progressive refinement network to refine alpha mattes generated utilizing a mask-guided matting neural network. In particular, the disclosed systems can use the matting neural network to process a digital image and a coarse guidance mask to generate alpha mattes at discrete neural network layers. In turn, the disclosed systems can use the progressive refinement network to combine alpha mattes and refine areas of uncertainty. For example, the progressive refinement network can combine a core alpha matte corresponding to more certain core regions of a first alpha matte and a boundary alpha matte corresponding to uncertain boundary regions of a second, higher resolution alpha matte. Based on the combination of the core alpha matte and the boundary alpha matte, the disclosed systems can generate a final alpha matte for use in image matting processes.

公开(公告)号：US20200372622A1

公开(公告)日：2020-11-26

申请号：US16984992

申请日：2020-08-04

Applicant: Adobe Inc.

Inventor： Yilin Wang ,  Zhe Lin ,  Zhaowen Wang ,  Xin Lu ,  Xiaohui Shen ,  Chih-Yao Hsieh

IPC: G06T5/50

Abstract: The present disclosure relates to training and utilizing an image exposure transformation network to generate a long-exposure image from a single short-exposure image (e.g., still image). In various embodiments, the image exposure transformation network is trained using adversarial learning, long-exposure ground truth images, and a multi-term loss function. In some embodiments, the image exposure transformation network includes an optical flow prediction network and/or an appearance guided attention network. Trained embodiments of the image exposure transformation network generate realistic long-exposure images from single short- exposure images without additional information.