-
公开(公告)号：US11050994B2
公开(公告)日：2021-06-29
申请号：US16891977
申请日：2020-06-03
Applicant: Adobe Inc.
IPC: H04N9/47 , H04N13/128 , G06T15/20 , G02B27/01 , G06N3/02 , G06T17/20 , G06N3/04 , G06N3/08 , H04N13/00
Abstract: Virtual reality parallax correction techniques and systems are described that are configured to correct parallax for VR digital content captured from a single point of origin. In one example, a parallax correction module is employed to correct artifacts caused in a change from a point of origin that corresponds to the VR digital content to a new viewpoint with respect to an output of the VR digital content. A variety of techniques may be employed by the parallax correction module to correct parallax. Examples of these techniques include depth filtering, boundary identification, smear detection, mesh cutting, confidence estimation, blurring, and error diffusion as further described in the following sections.
-
12.发明授权公开(公告)号：US10997464B2
公开(公告)日：2021-05-04
申请号：US16186382
申请日：2018-11-09
Applicant: Adobe Inc.
Inventor： Jimei Yang , Jianming Zhang , Aaron Phillip Hertzmann , Jianan Li
Abstract: Digital image layout training is described using wireframe rendering within a generative adversarial network (GAN) system. A GAN system is employed to train the generator module to refine digital image layouts. To do so, a wireframe rendering discriminator module rasterizes a refined digital training digital image layout received from a generator module into a wireframe digital image layout. The wireframe digital image layout is then compared with at least one ground truth digital image layout using a loss function as part of machine learning by the wireframe discriminator module. The generator module is then trained by backpropagating a result of the comparison.
-
公开(公告)号：US20200296348A1
公开(公告)日：2020-09-17
申请号：US16891977
申请日：2020-06-03
Applicant: Adobe Inc.
IPC: H04N13/128 , G06T15/20 , G02B27/01 , G06N3/02 , G06T17/20
Abstract: Virtual reality parallax correction techniques and systems are described that are configured to correct parallax for VR digital content captured from a single point of origin. In one example, a parallax correction module is employed to correct artifacts caused in a change from a point of origin that corresponds to the VR digital content to a new viewpoint with respect to an output of the VR digital content. A variety of techniques may be employed by the parallax correction module to correct parallax. Examples of these techniques include depth filtering, boundary identification, smear detection, mesh cutting, confidence estimation, blurring, and error diffusion as further described in the following sections.
-
Patent Agency Ranking
公开(公告)号：US10701334B2
公开(公告)日：2020-06-30
申请号：US15730478
申请日：2017-10-11
Applicant: Adobe Inc.
IPC: H04N13/02 , H04N13/128 , G06T15/20 , G02B27/01 , G06N3/02 , G06T17/20 , G06N3/04 , G06N3/08 , H04N13/00
Abstract: Virtual reality parallax correction techniques and systems are described that are configured to correct parallax for VR digital content captured from a single point of origin. In one example, a parallax correction module is employed to correct artifacts caused in a change from a point of origin that corresponds to the VR digital content to a new viewpoint with respect to an output of the VR digital content. A variety of techniques may be employed by the parallax correction module to correct parallax. Examples of these techniques include depth filtering, boundary identification, smear detection, mesh cutting, confidence estimation, blurring, and error diffusion as further described in the following sections.
-
15.发明公开公开(公告)号：US20230196630A1
公开(公告)日：2023-06-22
申请号：US17556716
申请日：2021-12-20
Applicant: Adobe Inc.
CPC classification number: G06T11/00 , G06V10/40 , G06N3/0454 , G06N3/084 , G06T2207/20081 , G06T2207/20084
Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a multi-stroke neural network for modifying a digital image via a plurality of generated stroke parameters in a single pass of the neural network. Specifically, the disclosed system utilizes an encoder neural network to generate an encoding of a digital image. The disclosed system then utilizes a decoder neural network that generates a sequence of stroke parameters for digital drawing strokes from the encoding in a single pass of the encoder neural network and decoder neural network. Additionally, the disclosed system utilizes a renderer neural network to render the digital drawing strokes on a digital canvas according to the sequence of stroke parameters. In additional embodiments, the disclosed system utilizes a balance of loss functions to learn parameters of the multi-stroke neural network to generate stroke parameters according to various rendering styles.
-
16.发明授权公开(公告)号：US11468294B2
公开(公告)日：2022-10-11
申请号：US16798271
申请日：2020-02-21
Applicant: Adobe Inc.
Inventor： Richard Zhang , Sylvain Philippe Paris , Junyan Zhu , Aaron Phillip Hertzmann , Jacob Minyoung Huh
Abstract: A target image is projected into a latent space of generative model by determining a latent vector by applying a gradient-free technique and a class vector by applying a gradient-based technique. An image is generated from the latent and class vectors, and a loss function is used to determine a loss between the target image and the generated image. This determining of the latent vector and the class vector, generating an image, and using the loss function is repeated until a loss condition is satisfied. In response to the loss condition being satisfied, the latent and class vectors that resulted in the loss condition being satisfied are identified as the final latent and class vectors, respectively. The final latent and class vectors are provided to the generative model and multiple weights of the generative model are adjusted to fine-tune the generative model.
-
公开(公告)号：US10803642B2
公开(公告)日：2020-10-13
申请号：US15680523
申请日：2017-08-18
Applicant: Adobe Inc.
IPC: G06T11/60 , G06F3/01 , H04L29/06 , G06F3/0346 , G06T19/00
Abstract: Techniques and systems to support collaborative interaction as part of virtual reality video are described. In one example, a viewport is generated such that a reviewing user of a reviewing user device may view VR video viewed by a source user of a source user device. The viewport, for instance, may be configured as a border at least partially surrounding a portion of the VR video output by the reviewing VR device. In another instance, the viewport is configured to support output of thumbnails within an output of VR video by the reviewing VR device. Techniques and systems are also described to support communication of annotations between the source and reviewing VR devices. Techniques and systems are also described to support efficient distribution of VR video within a context of a content editing application.
-
18.发明申请公开(公告)号：US20200151508A1
公开(公告)日：2020-05-14
申请号：US16186382
申请日：2018-11-09
Applicant: Adobe Inc.
Inventor： Jimei Yang , Jianming Zhang , Aaron Phillip Hertzmann , Jianan Li
Abstract: Digital image layout training is described using wireframe rendering within a generative adversarial network (GAN) system. A GAN system is employed to train the generator module to refine digital image layouts. To do so, a wireframe rendering discriminator module rasterizes a refined digital training digital image layout received from a generator module into a wireframe digital image layout. The wireframe digital image layout is then compared with at least one ground truth digital image layout using a loss function as part of machine learning by the wireframe discriminator module. The generator module is then trained by backpropagating a result of the comparison.
-
-
-
-
-
-
-
Search Results
18
records
(took 0.015 seconds)
