中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

13 records (took 0.016 seconds)

    Joint View Expansion And Filtering For Automultiscopic 3D Displays
    2.
    发明申请
    Joint View Expansion And Filtering For Automultiscopic 3D Displays 有权
    用于自动三维显示的联合视图扩展和过滤

    公开(公告)号：US20150124062A1

    公开(公告)日：2015-05-07

    申请号：US14531548

    申请日：2014-11-03

    Applicant: Massachusetts Institute of Technology

    Inventor： Piotr Krzysztof Didyk ,  Pitchaya Sitthi-Amorn ,  Wojciech Matusik ,  Frederic Durand ,  William T. Freeman

    IPC: H04N13/04

    CPC classification number: H04N13/302 ,  H04N13/111 ,  H04N13/122 ,  H04N13/128 ,  H04N13/351

    Abstract: Multi-view autostereoscopic displays provide an immersive, glasses-free 3D viewing experience, but they preferably use correctly filtered content from multiple viewpoints. The filtered content, however, may not be easily obtained with current stereoscopic production pipelines. The proposed method and system takes a stereoscopic video as an input and converts it to multi-view and filtered video streams that may be used to drive multi-view autostereoscopic displays. The method combines a phase-based video magnification and an interperspective antialiasing into a single filtering process. The whole algorithm is simple and may be efficiently implemented on current GPUs to yield real-time performance. Furthermore, the ability to retarget disparity is naturally supported. The method is robust and works transparent materials, and specularities. The method provides superior results when compared to the state-of-the-art depth-based rendering methods. The method is showcased in the context of a real-time 3D videoconferencing system.

    Abstract translation: 多视图自动立体显示器提供了沉浸式，无眼镜的3D观看体验，但是它们优选地从多个视点正确滤波内容。 然而，当前立体生产管道可能不容易获得过滤的内容。 所提出的方法和系统采用立体视频作为输入，并将其转换为可用于驱动多视点自动立体显示器的多视图和滤波视频流。 该方法将基于相位的视频放大和间隔抗锯齿组合到单个滤波过程中。 整个算法很简单，可以在当前的GPU上有效地实现，以实现实时性能。 此外，自然地支持重新定位差异的能力。 该方法是坚固的，透明的材料和镜面反射。 与最先进的基于深度的渲染方法相比，该方法提供了优异的结果。 该方法在实时3D视频会议系统的上下文中展示。

    SYSTEM AND METHOD FOR DESIGNING THREE-DIMENSIONAL OBJECTS
    3.
    发明申请
    SYSTEM AND METHOD FOR DESIGNING THREE-DIMENSIONAL OBJECTS 有权
    用于设计三维物体的系统和方法

    公开(公告)号：US20150066440A1

    公开(公告)日：2015-03-05

    申请号：US14316333

    申请日：2014-06-26

    Applicant: Massachusetts Institute of Technology

    Inventor： Desai Chen ,  Pitchaya Sitthi-Amorn ,  David I.W. Levin ,  Piotr Didyk ,  Wojciech Matusik

    IPC: G06F17/50 ,  G06T17/00

    CPC classification number: G06F17/50 ,  B33Y70/00 ,  G06F17/5009 ,  G06T17/00

    Abstract: According to some aspects, a method of designing an object based on a three-dimensional model representing a shape of the object is provided. The object may be fabricated from a plurality of materials having one or more known physical properties, wherein the object is designed to exhibit one or more target properties. The method may comprise determining a first composition of the object by providing the three-dimensional model as input to a reducer tree, determining one or more physical properties of the object with the first composition by simulating the object with the first composition, comparing the determined one or more physical properties with the one or more target properties, and determining a second composition of the object based on a result of comparing the determined one or more physical properties with the one or more target properties.

    Abstract translation: 根据一些方面，提供了一种基于表示对象的形状的三维模型来设计对象的方法。 该物体可以由具有一种或多种已知物理性质的多种材料制造，其中该物体被设计为展现一种或多种目标性质。 该方法可以包括通过将三维模型作为输入提供给减速器树来确定对象的第一组合，通过用第一组合模拟对象来确定具有第一组合的对象的一个​​或多个物理属性，将所确定的 一个或多个具有所述一个或多个目标属性的物理属性，以及基于将所确定的一个或多个物理属性与所述一个或多个目标属性进行比较的结果来确定所述对象的第二组成。

    SYSTEMS AND METHODS OF MACHINE VISION ASSISTED ADDITIVE FABRICATION
    4.
    发明申请
    SYSTEMS AND METHODS OF MACHINE VISION ASSISTED ADDITIVE FABRICATION 审中-公开

    公开(公告)号：US20200147888A1

    公开(公告)日：2020-05-14

    申请号：US16526068

    申请日：2019-07-30

    Applicant: Massachusetts Institute of Technology

    Inventor： Javier E. Ramos ,  Pitchaya Sitthi-Amorn ,  Wojciech Matusik ,  Yuwang Wang

    IPC: B29C64/386 ,  B29C64/106 ,  B29C64/393 ,  B33Y50/02 ,  B33Y30/00 ,  B33Y10/00

    Abstract: The present application relates generally to systems and methods for using machine vision to provide information on one or more aspects of an additive fabrication device, such as calibration parameters and/or an object formed by the device or in the process of being formed by the device. According to some aspects, a method is provided for calibrating an additive fabrication device. According to some aspects, a method is provided for assessing at least a portion of an object formed using an additive fabrication device. According to some aspects, a method is provided for fabricating a second object in contact with a first object using an additive fabrication device. According to some aspects, an additive fabrication device configured to perform one or more of the above methods may be provided.

    3DTV at home: Eulerian-Lagrangian stereo-to-multi-view conversion
    7.
    发明授权
    3DTV at home: Eulerian-Lagrangian stereo-to-multi-view conversion 有权

    公开(公告)号：US10834372B2

    公开(公告)日：2020-11-10

    申请号：US16000662

    申请日：2018-06-05

    Applicant: Massachusetts Institute of Technology

    Inventor： Wojciech Matusik ,  Piotr K. Didyk ,  William T. Freeman ,  Petr Kellnhofer ,  Pitchaya Sitthi-Amorn ,  Frederic Durand ,  Szu-Po Wang

    IPC: H04N13/111 ,  G06T7/593 ,  H04N13/128

    Abstract: A method and system of converting stereo video content to multi-view video content combines an Eulerian approach with a Lagrangian approach. The method comprises generating a disparity map for each of the left and right views of a received stereoscopic frame. For each corresponding pair of left and right scanlines of the received stereoscopic frame, the method further comprises decomposing the left and right scanlines into a left sum of wavelets or other basis functions, and a right sum wavelets or other basis functions. The method further comprises establishing an initial disparity correspondence between left wavelets and right wavelets based on the generated disparity maps, and refining the initial disparity between the left wavelet and the right wavelet using a phase difference between the corresponding wavelets. The method further comprises reconstructing at least one novel view based on the left and right wavelets.

    3dtv At Home: Eulerian-Lagrangian Stereo-To-Multi-View Conversion
    8.
    发明申请
    3dtv At Home: Eulerian-Lagrangian Stereo-To-Multi-View Conversion 审中-公开

    公开(公告)号：US20180352208A1

    公开(公告)日：2018-12-06

    申请号：US16000662

    申请日：2018-06-05

    Applicant: Massachusetts Institute of Technology

    Inventor： Wojciech Matusik ,  Piotr K. Didyk, Ph.D. ,  William T. Freeman ,  Petr Kellnhofer ,  Pitchaya Sitthi-Amorn ,  Frederic Durand ,  Szu-Po Wang

    IPC: H04N13/111 ,  G06T7/593 ,  H04N13/128

    Abstract: A method and system of converting stereo video content to multi-view video content combines an Eulerian approach with a Lagrangian approach. The method comprises generating a disparity map for each of the left and right views of a received stereoscopic frame. For each corresponding pair of left and right scanlines of the received stereoscopic frame, the method further comprises decomposing the left and right scanlines into a left sum of wavelets or other basis functions, and a right sum wavelets or other basis functions. The method further comprises establishing an initial disparity correspondence between left wavelets and right wavelets based on the generated disparity maps, and refining the initial disparity between the left wavelet and the right wavelet using a phase difference between the corresponding wavelets. The method further comprises reconstructing at least one novel view based on the left and right wavelets.

    Joint view expansion and filtering for automultiscopic 3D displays
    9.
    发明授权
    Joint view expansion and filtering for automultiscopic 3D displays 有权

    公开(公告)号：US09756316B2

    公开(公告)日：2017-09-05

    申请号：US14531548

    申请日：2014-11-03

    Applicant: Massachusetts Institute of Technology

    Inventor： Piotr Krzysztof Didyk ,  Pitchaya Sitthi-Amorn ,  Wojciech Matusik ,  Frederic Durand ,  William T. Freeman

    IPC: H04N13/04 ,  H04N13/00

    CPC classification number: H04N13/302 ,  H04N13/111 ,  H04N13/122 ,  H04N13/128 ,  H04N13/351

    Abstract: Multi-view autostereoscopic displays provide an immersive, glasses-free 3D viewing experience, but they preferably use correctly filtered content from multiple viewpoints. The filtered content, however, may not be easily obtained with current stereoscopic production pipelines. The proposed method and system takes a stereoscopic video as an input and converts it to multi-view and filtered video streams that may be used to drive multi-view autostereoscopic displays. The method combines a phase-based video magnification and an interperspective antialiasing into a single filtering process. The whole algorithm is simple and may be efficiently implemented on current GPUs to yield real-time performance. Furthermore, the ability to retarget disparity is naturally supported. The method is robust and works transparent materials, and specularities. The method provides superior results when compared to the state-of-the-art depth-based rendering methods. The method is showcased in the context of a real-time 3D videoconferencing system.

Patent Agency Ranking