专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20180239434A1 Stroke Operation Prediction for Three-Dimensional Digital Content 审中-公开
公开(公告)号：US20180239434A1
公开(公告)日：2018-08-23
申请号：US15438276
申请日：2017-02-21
申请人： Adobe Systems Incorporated
发明人： Jingwan Lu , Stephen J. DiVerdi , Byungmoon Kim , Jun Xing
IPC分类号： G06F3/01
CPC分类号： G06F3/017 , G06F3/011 , G06F3/0346 , G06F3/0488 , G06T11/203 , G06T15/02 , G06T17/30 , G06T19/00
摘要： Stroke operation prediction techniques and systems for three-dimensional digital content are described. In one example, stroke operation data is received that describes a stroke operation input via a user interface as part of the three-dimensional digital content. A cycle is generated that defines a closed path within the three-dimensional digital content based on the input stroke operation and at least one other stroke operation in the user interface. A surface is constructed based on the generated cycle. A predicted stroke operation is generated based at least in part on the constructed surface. The predicted stroke operation is then output in real time in the user interface as part of the three-dimensional digital content as the stroke operation data is received.

2. 发明授权

US09990565B2 Methods for object recognition and related arrangements 有权
公开(公告)号：US09990565B2
公开(公告)日：2018-06-05
申请号：US15332262
申请日：2016-10-24
申请人： Digimarc Corporation
发明人： Geoffrey B. Rhoads , Yang Bai , Tony F. Rodriguez , Eliot Rogers , Ravi K. Sharma , John D. Lord , Scott Long , Brian T. MacIntosh , Kurt M. Eaton
IPC分类号： G06K9/00 , G06K9/62 , G06T15/20 , H04N7/18 , G06F17/30
CPC分类号： G06K9/6215 , G06F17/30247 , G06F17/30256 , G06F17/30268 , G06K9/00 , G06K9/00208 , G06K9/4671 , G06K9/6202 , G06K9/6255 , G06T15/02 , G06T15/20 , G06T17/00 , H04N7/185
摘要： Methods and arrangements involving portable user devices such smartphones and wearable electronic devices are disclosed, as well as other devices and sensors distributed within an ambient environment. Some arrangements enable a user to perform an object recognition process in a computationally- and time-efficient manner. Other arrangements enable users and other entities to, either individually or cooperatively, register or enroll physical objects into one or more object registries on which an object recognition process can be performed. Still other arrangements enable users and other entities to, either individually or cooperatively, associate registered or enrolled objects with one or more items of metadata. A great variety of other features and arrangements are also detailed.

3. 发明授权

US09978342B2 Image processing method controlling image display based on gaze point and recording medium therefor 有权
公开(公告)号：US09978342B2
公开(公告)日：2018-05-22
申请号：US15135639
申请日：2016-04-22
申请人： Koei Tecmo Games Co., Ltd.
发明人： Ryota Sakamoto
IPC分类号： G09G5/36 , G06F3/01 , G06T17/20 , G06T15/80 , G06T3/00 , G06F1/16 , G06T15/02 , G06F3/147 , G09G5/391
CPC分类号： G09G5/363 , G06F1/163 , G06F3/011 , G06F3/013 , G06F3/147 , G06T3/00 , G06T15/02 , G06T15/80 , G06T17/20 , G06T2210/36 , G09G5/391 , G09G2320/0613 , G09G2320/08 , G09G2340/0407 , G09G2340/12 , G09G2340/14 , G09G2354/00 , G09G2370/16
摘要： An information processing device communicably connected to a head mounted display including a display device displaying an image and a sight line detector detecting a user's line of sight is caused to function as a drawing control part. The drawing control part controls drawing of the image such that the drawing is simplified in a peripheral region of a user's gaze point as compared to a vicinity region of the gaze point based on information on the user's line of sight detected by the sight line detector.

4. 发明申请

US20150254903A1 Augmented Reality Image Transformation 有权
标题翻译：增强现实图像转换
公开(公告)号：US20150254903A1
公开(公告)日：2015-09-10
申请号：US14626799
申请日：2015-02-19
申请人： Disney Enterprises, Inc.
发明人： Robert Sumner , Maurizio Nitti , Gerhard Roethlin , Alessia Marra , Mattia Ryffel , Gioacchino Noris , Kenny Mitchell , Stephane Magnenat
IPC分类号： G06T19/00 , G06T15/04 , G06T17/10
CPC分类号： G06T19/006 , G06T15/02 , G06T15/04 , G06T19/20 , G06T2219/2012
摘要： There is provided a system and method for augmented reality image transformation. In one implementation, such a system includes a system processor, a system memory, and an image transformation engine stored in the system memory. The system processor is configured to execute the image transformation engine to receive image data corresponding to an image, to detect a feature on a surface of the image, and to synthesize a texture corresponding to the feature. The system processor is further configured to execute the image transformation engine to produce an augmented reality representation of the image having the texture for display to a user, the texture covering a surface of the augmented reality representation of the image corresponding to a portion of the feature that is not visible on the surface of the image.
摘要翻译：提供了一种用于增强现实图像变换的系统和方法。在一个实现中，这样的系统包括系统处理器，系统存储器和存储在系统存储器中的图像转换引擎。系统处理器被配置为执行图像变换引擎以接收对应于图像的图像数据，以检测图像的表面上的特征，并且合成与该特征相对应的纹理。系统处理器还被配置为执行图像变换引擎以产生具有用于向用户显示的纹理的图像的增强现实表示，纹理覆盖对应于特征的一部分的图像的增强现实表示的表面这在图像的表面上是不可见的。

5. 发明授权

US09110572B2 Network based video creation 有权
标题翻译：网络视频制作
公开(公告)号：US09110572B2
公开(公告)日：2015-08-18
申请号：US13758109
申请日：2013-02-04
申请人： Visible Spectrum, Inc.
发明人： Baron Gerhardt , John Malec , Sam Melton , Aaron Taylor
IPC分类号： G06F3/00 , G06F3/0484 , G06T11/00 , G06T15/02
CPC分类号： G06F3/0484 , G06T11/00 , G06T15/02 , G11B27/031 , G11B27/34
摘要： A computing device is configured to provide over a network an ability to create a 2.5D full motion custom multi-media file. In one example, a computing device makes available to a user a plurality of stored video templates into which a user may insert custom video, photos, and/or text. The computing device provides a low resolution preview of the custom video to the user over the network connection. The user then has the ability to edit the custom video prior to finalization. The computing device receives signals indicating purchase or licensing credentials and in response to receiving such credentials, finalizes and delivers a 2.5D video for the user. So configured, a user can relatively cheaply and quickly create video content such as an advertisement having modern visual features such as 2.5D video in a cost efficient and timely manner.
摘要翻译：计算设备被配置为通过网络提供创建2.5D全动态自定义多媒体文件的能力。在一个示例中，计算设备向用户提供多个存储的视频模板，用户可以在其中插入自定义视频，照片和/或文本。计算设备通过网络连接向用户提供定制视频的低分辨率预览。用户然后可以在定稿之前编辑自定义视频。计算设备接收指示购买或许可凭证的信号，并且响应于接收到这样的凭证，为用户确定并递送2.5D视频。如此配置，用户可以以成本有效和及时的方式相对便宜地并且快速地创建诸如具有现代视觉特征（例如2.5D视频）的广告的视频内容。

6. 发明申请

US20140267350A1 STYLIZING ANIMATION BY EXAMPLE 有权
标题翻译：通过实例进行动画化
公开(公告)号：US20140267350A1
公开(公告)日：2014-09-18
申请号：US13829602
申请日：2013-03-14
申请人： PIXAR
发明人： Michael KASS , Pierre BENARD , Forrester COLE
IPC分类号： G06T13/00
CPC分类号： G06T15/02 , G06T11/60 , G06T13/80 , G06T15/005 , G09G5/02 , G09G5/393 , H04N7/142 , H04N19/61
摘要： The disclosure provides an approach for stylizing animations to synthesize example textures. In one embodiment, a synthesis application down-samples input and style buffers. To obtain a sequence of offset fields, each of which takes pixels in the output stylized frame to corresponding pixels in the stylized example image, the synthesis application may optimize each frame of the animation at level l−1, then advect the results of a previous frame to a next frame using velocity fields. After having processed the entire animation sequence forward through time, a similar sweep may be performed backwards. Then, the resulting offset fields may be up-sampled to level l and used as the starting point for optimization at that finer level of detail. This process may be repeated until returning to the original sampling, which yields the final output.
摘要翻译：本公开提供了用于对动画进行风格化以合成示例纹理的方法。在一个实施例中，合成应用程序降低样本输入和样式缓冲区。为了获得偏移场序列，其中的每一个将输出风格化帧中的像素取为风格化示例图像中的对应像素，合成应用可以优化级别1-l处的动画的每个帧，然后平滑先前帧到使用速度场的下一帧。经过时间处理整个动画序列后，可能会向后执行类似的扫描。然后，所得到的偏移字段可以被上采样到级别l，并用作在更细的细节级别进行优化的起始点。可以重复该过程，直到返回到原始采样，其产生最终输出。

7. 发明授权

US08786902B2 Image processing apparatus, method and printer for generating three-dimensional painterly image 有权
标题翻译：用于生成立体画面图像的图像处理装置，方法和打印机
公开(公告)号：US08786902B2
公开(公告)日：2014-07-22
申请号：US13549749
申请日：2012-07-16
申请人： Yoshiyuki Murata
发明人： Yoshiyuki Murata
IPC分类号： H04N1/60
CPC分类号： B41F17/00 , B33Y50/02 , G01C3/32 , G03B17/48 , G06T11/001 , G06T15/02 , H04N1/00127 , H04N1/00323 , H04N5/2621 , H04N2101/00 , H04N2201/0055
摘要： An image processing apparatus includes an image acquiring unit, a distance acquiring unit, a painterly transformation processor, a thickness information acquiring unit, and a data generating unit. The distance acquiring unit acquires distance information for each of at least one object image included in an acquired image. The painterly transformation processor transforms each of the object image, included in the acquired image, into a painterly image. The thickness information acquiring unit acquires thickness information corresponding to the distance for each of the object image. The data generating unit generates data in which the painterly image and the thickness information are associated with each other.
摘要翻译：图像处理装置包括图像获取单元，距离获取单元，画家变换处理器，厚度信息获取单元和数据生成单元。距离获取单元获取包括在所获取的图像中的至少一个对象图像中的每一个的距离信息。画家变换处理器将包含在所获取的图像中的每个对象图像变换成画面图像。厚度信息获取单元获取与每个对象图像的距离相对应的厚度信息。数据生成单元生成绘画图像和厚度信息相互关联的数据。

8. 发明授权

US08760466B1 Coherent noise for non-photorealistic rendering 有权
标题翻译：相干噪声用于非真实感渲染
公开(公告)号：US08760466B1
公开(公告)日：2014-06-24
申请号：US12854059
申请日：2010-08-10
申请人： Michael Kass , Davide Pesare
发明人： Michael Kass , Davide Pesare
IPC分类号： G09G5/00
CPC分类号： G06T13/80 , G06T5/002 , G06T11/00 , G06T15/02
摘要： A method for generating two-dimensional image space noise. The method includes receiving a first frame of a rendered animation sequence; receiving a second frame of the rendered animation sequence; and generating a frame of noise that is associated with at least one object moving between the first frame and the second frame and is to be applied to the second frame, where generating the frame of noise comprises applying, for each pixel in the second frame, a causal filter based on a depth associated with the pixel and a velocity associated with the pixel.
摘要翻译：一种产生二维图像空间噪声的方法。该方法包括接收渲染动画序列的第一帧; 接收所渲染的动画序列的第二帧; 以及产生与在所述第一帧和所述第二帧之间移动的至少一个物体相关联并将被施加到所述第二帧的噪声的帧，其中产生所述噪声的帧包括：对于所述第二帧中的每个像素，基于与像素相关联的深度和与像素相关联的速度的因果滤波器。

9. 发明授权

US08508529B2 Methods and systems of generating a three dimensional model based on a plurality of images 有权
标题翻译：基于多个图像生成三维模型的方法和系统
公开(公告)号：US08508529B2
公开(公告)日：2013-08-13
申请号：US12836611
申请日：2010-07-15
申请人： Gershon Elber
发明人： Gershon Elber
IPC分类号： G06T17/00
CPC分类号： G06T15/02
摘要： A method of creating a three dimensional (3D ) model which demonstrates two or three images. The method comprises rendering first and second (and optionally third) images, adjust the plurality of primitives along a first axis of the 3D space according to the first image and along a second axis of the 3D space according to the second image (and optionally, and along a third axis of the 3D space according to the third image), and creating a 3D model which demonstrates the first and second (and optionally third) images according to the plurality of adjusted primitives in the 3D space. The first and second (and optionally third) axes are independent view directions.
摘要翻译：创建演示两个或三个图像的三维（3D）模型的方法。该方法包括渲染第一和第二（和任选地第三）图像，根据第一图像沿着3D空间的第一轴并沿着根据第二图像的3D空间的第二轴来调整多个图元（并且可选地，并且沿着根据第三图像的3D空间的第三轴），并且创建根据3D空间中的多个经调整的图元来演示第一和第二（和可选地第三）图像的3D模型。第一和第二（和任选的第三）轴是独立的视图方向。

10. 发明申请

US20120075284A1 Computer Method and Apparatus for Rotating 2D Cartoons Using 2.5D Cartoon Models 有权
标题翻译：使用2.5D卡通模型旋转2D卡通的计算机方法和装置
公开(公告)号：US20120075284A1
公开(公告)日：2012-03-29
申请号：US12889937
申请日：2010-09-24
申请人： Alec Rivers , Frederic Durand
发明人： Alec Rivers , Frederic Durand
IPC分类号： G06T15/00
CPC分类号： G06T15/02 , G06T3/4007
摘要： Disclosed herein are methods, apparatus, and computer program programs that use 2D drawings of a cartoon in different views to automatically construct rotated views of the subject cartoon. Embodiments involve a novel structure, the 2.5D cartoon model, which can generate plausible renderings of the cartoon in any view. Two or more input drawings can be leveraged to construct a 2.5D cartoon model that supports full 3D rotation. Unlike a 3D model, however, renderings produced by a 2.5D cartoon model retain the 2D nature and hand-drawn appearance of the input drawings, and support a wide range of 2D stylizations and shapes that would be impossible with a 3D model.
摘要翻译：本文公开了使用不同视图中的卡通的2D图纸以自动构建主题卡通的旋转视图的方法，装置和计算机程序程序。实施例涉及一种新颖的结构，2.5D卡通模型，可以在任何视图中产生卡通的合理效果。可以利用两个或多个输入图来构建一个支持全3D旋转的2.5D卡通模型。然而，与3D模型不同，2.5D卡通模型生成的渲染保留了输入图形的2D特征和手绘外观，并支持3D模型不可能实现的广泛的二维风格和形状。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式