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. 发明授权

US09609307B1 Method of converting 2D video to 3D video using machine learning 有权
公开(公告)号：US09609307B1
公开(公告)日：2017-03-28
申请号：US14967939
申请日：2015-12-14
申请人： LEGEND3D, INC.
发明人： Anthony Lopez , Jacqueline McFarland , Tony Baldridge
IPC分类号： G06K9/00 , H04N13/02 , H04N13/00
CPC分类号： H04N13/122 , G06T7/557 , G06T2207/20081 , H04N13/128 , H04N13/261
摘要： Machine learning method that learns to convert 2D video to 3D video from a set of training examples. Uses machine learning to perform any or all of the 2D to 3D conversion steps of identifying and locating objects, masking objects, modeling object depth, generating stereoscopic image pairs, and filling gaps created by pixel displacement for depth effects. Training examples comprise inputs and outputs for the conversion steps. The machine learning system generates transformation functions that generate the outputs from the inputs; these functions may then be used on new 2D videos to automate or semi-automate the conversion process. Operator input may be used to augment the results of the machine learning system. Illustrative representations for conversion data in the training examples include object tags to identify objects and locate their features, Bézier curves to mask object regions, and point clouds or geometric shapes to model object depth.

2. 发明授权

US09443555B2 Multi-stage production pipeline system 有权
公开(公告)号：US09443555B2
公开(公告)日：2016-09-13
申请号：US15050381
申请日：2016-02-22
申请人： LEGEND3D, Inc.
发明人： Barry Sandrew , Jared Sandrew , Nancy Wang , Craig Cesareo , James Prola , Jill Hunt , Anthony Lopez
IPC分类号： H04N7/18 , G11B27/031 , G11B27/34 , H04N21/472 , H04N13/00 , H04N13/02 , G06F17/30 , G06Q10/10 , H04N9/79
CPC分类号： G11B27/036 , G06F17/30247 , G06F17/30256 , G06F17/30268 , G06F17/30784 , G06F17/3082 , G06Q10/103 , G11B27/031 , G11B27/34 , H04N9/79 , H04N13/128 , H04N13/15 , H04N13/189 , H04N13/257 , H04N13/261 , H04N13/266 , H04N21/47205
摘要： Multi-stage production pipeline system that may be utilized in conjunction with a motion picture project management system. The multi-stage production pipeline system includes a computer and a database. The database includes metadata associated with at least one shot or associated with regions within the plurality of images in the at least one shot, or both. The computer includes a grouping tool interface for presenting user interface elements and accepting input of the metadata associated with the at least one shot or regions within the plurality of images in the at least one shot, or both. The system enables a large studio workforce to work non-linearly on a film while maintaining a unified vision driven by key creative figures, allowing for more consistent, higher quality, faster, less expensive work product and more efficient project management techniques. The system also enables reuse of project files, masks and other production elements across projects.

3. 发明授权

US09277122B1 System and method for removing camera rotation from a panoramic video 有权
标题翻译：从全景视频中删除相机旋转的系统和方法
公开(公告)号：US09277122B1
公开(公告)日：2016-03-01
申请号：US14825746
申请日：2015-08-13
申请人： Legend3D, Inc.
发明人： Ken Imura , Ryan Cummins
IPC分类号： H04N7/00 , H04N5/232 , G06T19/00 , G06T7/00
CPC分类号： H04N5/23238 , G06T7/246 , G06T7/292 , G06T7/73 , G06T19/003 , G06T19/006 , G06T2200/04 , G06T2207/10016 , H04N5/23254 , H04N5/23267 , H04N13/239
摘要： Removes undesirable camera rotation from a panoramic video. Video frames are mapped to a sphere and then projected to a forward-looking planar video. Camera tracking or other techniques are used to derive camera position and orientation in each frame. From the camera orientation, a correcting rotation is derived and is applied to the sphere onto which the panoramic video was mapped. Re-projecting video from the rotation-corrected sphere reduces or eliminates camera rotation artifacts from the panoramic video. Rotation may be re-introduced and other visual effects may be added to the stabilized video. May be utilized in 2D virtual reality and augmented reality displays. Depth may be accepted by the system for objects in the video and utilized to create 3D stereoscopic virtual reality and augmented reality displays.
摘要翻译：从全景视频中移除不需要的相机旋转。视频帧映射到球体，然后投影到前瞻性平面视频。摄像机跟踪或其他技术用于获取每帧中的摄像机位置和方位。从相机方向，导出校正旋转并将其应用于全景视频映射到的球体上。从旋转校正球重新投影视频会减少或消除全景视频中的相机旋转伪影。可以重新引入旋转，并且可以将其他视觉效果添加到稳定视频中。可用于2D虚拟现实和增强现实显示。深度可以由系统接受视频中的对象并用于创建3D立体虚拟现实和增强现实显示。

4. 发明申请

US20150358612A1 SYSTEM AND METHOD FOR REAL-TIME DEPTH MODIFICATION OF STEREO IMAGES OF A VIRTUAL REALITY ENVIRONMENT 有权
标题翻译：虚拟现实环境立体图像实时深度修改的系统与方法
公开(公告)号：US20150358612A1
公开(公告)日：2015-12-10
申请号：US14827422
申请日：2015-08-17
申请人： LEGEND3D, Inc.
发明人： Jared SANDREW , Tony BALDRIDGE , Anthony LOPEZ , Jacqueline MCFARLAND , Scott JONES , Thomas SCHAD
IPC分类号： H04N13/02 , H04N5/232
CPC分类号： H04N13/271 , G06T15/205 , G06T17/00 , H04N5/23238 , H04N13/122 , H04N13/128 , H04N13/243 , H04N13/257 , H04N13/261 , H04N13/296
摘要： Enables real-time depth modifications to stereo images of a 3D virtual reality environment locally and for example without iterative workflow involving region designers or depth artists that includes re-rendering these images from the original 3D model. Embodiments generate a spherical translation map from the 3D model of the virtual environment; this spherical translation map is a function of the pixel shifts between left and right stereo images for each point of the sphere surrounding the viewer of the virtual environment. Modifications may be made directly to the spherical translation map, and applied directly to the stereo images, without requiring re-rendering of the scene from the complete 3D model. This process enables depth modifications to be viewed in real-time, greatly improving the efficiency of the 3D model creation, review, and update cycle.
摘要翻译：实现对本地3D虚拟现实环境的立体图像进行实时深度修改，例如，无需涉及区域设计师或深度艺术家的迭代工作流程，包括从原始3D模型重新渲染这些图像。实施例从虚拟环境的3D模型生成球面平移图; 该球面平移映射是围绕虚拟环境的观察者的球体的每个点的左和右立体图像之间的像素移动的函数。可以直接对球面平移图进行修改，并且直接应用于立体图像，而不需要从完整的3D模型重新渲染场景。该过程使得能够实时观察深度修改，大大提高了3D模型创建，审查和更新周期的效率。

5. 发明授权

US09031383B2 Motion picture project management system 有权
标题翻译：电影项目管理系统
公开(公告)号：US09031383B2
公开(公告)日：2015-05-12
申请号：US13366899
申请日：2012-02-06
申请人： Jared Sandrew , Anthony Lopez , Timothy Tranquill , Craig Cesareo
发明人： Jared Sandrew , Anthony Lopez , Timothy Tranquill , Craig Cesareo
IPC分类号： H04N5/93 , G11B27/034 , G11B27/00 , G11B27/10
CPC分类号： G11B27/034 , G11B27/00 , G11B27/105 , H04N13/257 , H04N13/266
摘要： Motion picture project management system for reviewers, coordinators and artists. Artists utilize image analysis and image enhancement and computer graphics processing for example to convert two-dimensional images into three-dimensional images or otherwise create or alter motion pictures. Enables the efficient management of projects related to motion pictures to enable enterprises to manage assets, control costs, predict budgets and profit margins, reduce archival storage and otherwise provide displays tailored to specific roles to increase worker efficiency.
摘要翻译：电影项目管理系统供评审员，协调员和艺术家参考。艺术家利用图像分析和图像增强以及计算机图形处理来例如将二维图像转换为三维图像或以其他方式创建或改变运动图像。实现与电影相关的项目的有效管理，使企业能够管理资产，控制成本，预测预算和利润率，减少档案存储，并提供针对特定角色定制的显示器，以提高工作效率。

6. 发明申请

US20170085863A1 METHOD OF CONVERTING 2D VIDEO TO 3D VIDEO USING MACHINE LEARNING 有权
公开(公告)号：US20170085863A1
公开(公告)日：2017-03-23
申请号：US14967939
申请日：2015-12-14
申请人： LEGEND3D, INC.
发明人： Anthony LOPEZ , Jacqueline McFARLAND , Tony BALDRIDGE
IPC分类号： H04N13/02 , H04N13/00
CPC分类号： H04N13/122 , G06T7/557 , G06T2207/20081 , H04N13/128 , H04N13/261
摘要： Machine learning method that learns to convert 2D video to 3D video from a set of training examples. Uses machine learning to perform any or all of the 2D to 3D conversion steps of identifying and locating objects, masking objects, modeling object depth, generating stereoscopic image pairs, and filling gaps created by pixel displacement for depth effects. Training examples comprise inputs and outputs for the conversion steps. The machine learning system generates transformation functions that generate the outputs from the inputs; these functions may then be used on new 2D videos to automate or semi-automate the conversion process. Operator input may be used to augment the results of the machine learning system. Illustrative representations for conversion data in the training examples include object tags to identify objects and locate their features, Bézier curves to mask object regions, and point clouds or geometric shapes to model object depth.

7. 发明授权

US09438878B2 Method of converting 2D video to 3D video using 3D object models 有权
标题翻译：使用3D对象模型将2D视频转换为3D视频的方法
公开(公告)号：US09438878B2
公开(公告)日：2016-09-06
申请号：US14857704
申请日：2015-09-17
申请人： LEGEND3D, Inc.
发明人： Vicente Niebla, Jr. , Tony Baldridge , Thomas Schad , Scott Jones
IPC分类号： G06K9/00 , H04N13/00 , H04N13/02
CPC分类号： H04N13/128 , G06T7/557 , H04N13/122 , H04N13/261
摘要： Method for converting 2D video to 3D video using 3D object models. Embodiments of the invention obtain a 3D object model for one or more objects in a 2D video scene, such as a character. Object models may for example be derived from 3D scanner data; planes, polygons, or surfaces may be fit to this data to generate a 3D model. In each frame in which a modeled object appears, the location and orientation of the 3D model may be determined in the frame, and a depth map for the object may be generated from the model. 3D video may be generated using the depth map. Embodiments may use feature tracking to automatically determine object location and orientation. Embodiments may use rigged 3D models with degrees of freedom to model objects with parts that move relative to one another.
摘要翻译：使用3D对象模型将2D视频转换为3D视频的方法。本发明的实施例为诸如字符的2D视频场景中的一个或多个对象获得3D对象模型。对象模型可以例如从3D扫描器数据导出; 平面，多边形或曲面可以适合该数据以生成3D模型。在其中出现建模对象的每个帧中，可以在帧中确定3D模型的位置和方向，并且可以从模型生成对象的深度图。可以使用深度图生成3D视频。实施例可以使用特征跟踪来自动确定对象位置和方位。实施例可以使用具有自由度的装配3D模型来对具有相对于彼此移动的部件来建模对象。

8. 发明授权

US09286941B2 Image sequence enhancement and motion picture project management system 有权
标题翻译：图像序列增强和电影项目管理系统
公开(公告)号：US09286941B2
公开(公告)日：2016-03-15
申请号：US14709300
申请日：2015-05-11
申请人： LEGEND3D, Inc.
发明人： Barry Sandrew , Tony Baldridge , Jared Sandrew , Anthony Lopez
IPC分类号： H04N5/93 , G11B27/031 , H04N13/02
CPC分类号： H04N13/261 , G11B27/031 , H04N13/257 , H04N13/266
摘要： The system enables conversion of black and white images to color images and/or two-dimensional images into three-dimensional images based on adding color and/or depth to images using masks for regions in the images, as well as reshaping of masks to cover objects that have moved and changed shape as the objects move in a sequence of images. Also, includes motion picture project management system for reviewers, coordinators and artists. Artists utilize image analysis and image enhancement and computer graphics processing for example to convert two-dimensional images into three-dimensional images or otherwise create or alter motion pictures. Enables the efficient management of projects related to motion pictures to enable enterprises to manage assets, control costs, predict budgets and profit margins, reduce archival storage and otherwise provide displays tailored to specific roles to increase worker efficiency.
摘要翻译：该系统能够基于使用图像中的区域的掩模对图像添加颜色和/或深度来将黑白图像转换为彩色图像和/或二维图像成为三维图像，以及重新整形掩模以覆盖随着对象在一系列图像中移动，已经移动和改变形状的对象。此外，还包括评审员，协调员和艺术家的电影项目管理系统。艺术家利用图像分析和图像增强以及计算机图形处理来例如将二维图像转换为三维图像或以其他方式创建或改变运动图像。实现与电影相关的项目的有效管理，使企业能够管理资产，控制成本，预测预算和利润率，减少档案存储，并提供针对特定角色定制的显示器，以提高工作效率。

9. 发明授权

US08897596B1 System and method for rapid image sequence depth enhancement with translucent elements 有权
标题翻译：用半透明元素快速图像序列深度增强的系统和方法
公开(公告)号：US08897596B1
公开(公告)日：2014-11-25
申请号：US13367316
申请日：2012-02-06
申请人： Charles Passmore , Tony Baldridge , Barry Sandrew
发明人： Charles Passmore , Tony Baldridge , Barry Sandrew
IPC分类号： G06K9/00
CPC分类号： H04N13/266 , H04N13/257
摘要： Motion picture scenes to be colorized/depth enhanced (2D→3D) are broken into separate elements, backgrounds/sets or motion/onscreen-action. Background and motion elements are combined into composite frame which becomes a visual reference database that includes data for all frame offsets used later for the computer controlled application of masks within a sequence of frames. Masks are applied to subsequent frames of motion objects based on various differentiating image processing methods, including automated mask fitting/reshaping. Colors and/or depths are automatically applied to masks throughout a scene from the composite background, translucent, motion objects. Areas never exposed by motion or foreground objects in a series of images may be partially or fully realistically drawn or rendered and applied to the occluded areas of the background and then automatically applied throughout the images to generate of minimal artifact or artifact-free secondary viewpoints when translating foreground objects horizontally during 2D→3D conversion.
摘要翻译：要被着色/深度增强的动态影像场景（2D→3D）被分为单独的元素，背景/集合或运动/屏幕动作。背景和运动元素被组合成复合帧，其成为视觉参考数据库，其包括用于稍后在计算机控制的帧序列内的掩码的所有帧偏移的数据。基于各种差异化图像处理方法，包括自动掩模拟合/重新成形，将掩模应用于后续运动对象帧。颜色和/或深度自动应用于从复合背景，半透明，运动对象的场景中的蒙版。一系列图像中未被运动或前景物体暴露的区域可能部分或完全实际绘制或渲染并应用于背景的遮挡区域，然后自动应用于整个图像，以产生最少的伪像或无伪影次要视点，在2D→3D转换期间水平地翻译前景对象。

10. 发明授权

US08385684B2 System and method for minimal iteration workflow for image sequence depth enhancement 有权
标题翻译：用于图像序列深度增强的最小迭代工作流的系统和方法
公开(公告)号：US08385684B2
公开(公告)日：2013-02-26
申请号：US13029862
申请日：2011-02-17
申请人： Jared Sandrew , Tony Baldridge , Barry Sandrew
发明人： Jared Sandrew , Tony Baldridge , Barry Sandrew
IPC分类号： G06K9/36
CPC分类号： H04N13/257 , H04N13/266
摘要： Movies to be colorized/depth enhanced (2D->3D) are broken into backgrounds/sets or motion/onscreen-action. Background and motion elements are combined into composite frame which becomes a visual reference database that includes data for all frame offsets used later for the computer controlled application of masks within a sequence of frames. Masks are applied to subsequent frames of motion objects based on various differentiating image processing methods, including automated mask fitting/reshaping. Colors/depths are automatically applied with masks throughout a scene from the composite background and to motion objects. Areas never exposed by motion or foreground objects may be partially or fully realistically drawn/rendered/applied to the occluded areas and applied throughout the images to generate artifact-free secondary viewpoints during 2D->3D conversion. Iterative workflow is eliminated for simple artifact correction through real-time manipulation of images to avoid re-rendering of images and associated delays of sending work product to other workgroups for correction.
摘要翻译：要着色/深度增强的电影（2D-> 3D）被分为背景/集合或运动/屏幕动作。背景和运动元素被组合成复合帧，其成为视觉参考数据库，其包括用于稍后在计算机控制的帧序列内的掩码的所有帧偏移的数据。基于各种差异化图像处理方法，包括自动掩模拟合/重新成形，将掩模应用于后续运动对象帧。颜色/深度自动应用于整个场景中的掩模，从复合背景和运动对象。未被运动或前景物体曝光的区域可能部分或完全实际绘制/渲染/应用于遮挡区域，并在整个图像中应用，以在2D-> 3D转换期间生成无伪影次要视点。迭代工作流程通过实时处理图像来消除简单的伪像纠正，避免重新渲染图像，并将工作产品发送到其他工作组进行更正的相关延迟。

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