公开(公告)号：US20200074589A1

公开(公告)日：2020-03-05

申请号：US16121978

申请日：2018-09-05

Applicant: Toyota Research Institute, Inc. ,  Massachusetts Institute of Technology

Inventor： Simon A.I. Stent ,  Adrià Recasens ,  Antonio Torralba ,  Petr Kellnhofer ,  Wojciech Matusik

IPC: G06T3/40 ,  G06K9/46 ,  G06N3/08 ,  G06F3/01

Abstract: A method includes receiving, with a computing device, an image, identifying one or more salient features in the image, and generating a saliency map of the image including the one or more salient features. The method further includes sampling the image based on the saliency map such that the one or more salient features are sampled at a first density of sampling and at least one portion of the image other than the one or more salient features are sampled at a second density of sampling, where the first density of sampling is greater than the second density of sampling, and storing the sampled image in a non-transitory computer readable memory.

公开(公告)号：US10456984B2

公开(公告)日：2019-10-29

申请号：US15843543

申请日：2017-12-15

Applicant: Massachusetts Institute of Technology

Inventor： Wojciech Matusik ,  Allen S. Park ,  Javier E. Ramos ,  Kiril Vidimce

IPC: B33Y50/02 ,  B29C64/393 ,  B29C64/112 ,  B29C64/124 ,  G05B19/4099 ,  B33Y30/00 ,  B33Y10/00

Abstract: A closed-loop adaptive material deposition apparatus and method uses a scanning system to monitor an additively manufactured object as it is being fabricated and adapting the geometric shape and material composition of the subsequent layers based on the scan data. The scanning system repeatedly captures geometric and/or material information of a partially manufactured object with optional auxiliary objects inserted during the manufacturing process. Based on this information, the actual surface geometry and/or actual material composition is computed. Surface geometry may be offset and used as a slicing surface for the next portion of the digital model. The shape of the slicing surface may then be recomputed each time the system scans the partially fabricated object.

公开(公告)号：US20180194066A1

公开(公告)日：2018-07-12

申请号：US15582320

申请日：2017-04-28

Applicant: Massachusetts Institute of Technology

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

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

CPC classification number: B29C64/386 ,  B29C64/106 ,  B29C64/112 ,  B29C64/393 ,  B33Y10/00 ,  B33Y30/00 ,  B33Y50/02

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.

公开(公告)号：US09767226B2

公开(公告)日：2017-09-19

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 ,  B33Y70/00

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.

公开(公告)号：US20160023403A1

公开(公告)日：2016-01-28

申请号：US14645616

申请日：2015-03-12

Applicant: Massachusetts Institute of Technology

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

IPC: B29C67/00

CPC classification number: B29C64/386 ,  B29C64/106 ,  B29C64/112 ,  B29C64/393 ,  B33Y10/00 ,  B33Y30/00 ,  B33Y50/02

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.

Abstract translation: 本申请一般涉及用于使用机器视觉来提供关于添加制造装置的一个或多个方面的信息的系统和方法，诸如校准参数和/或由该装置形成的物体或在由装置形成的过程中 。 根据一些方面，提供了一种用于校准添加剂制造装置的方法。 根据一些方面，提供了一种用于评估使用添加剂制造装置形成的物体的至少一部分的方法。 根据一些方面，提供了一种用于使用添加剂制造装置制造与第一物体接触的第二物体的方法。 根据一些方面，可以提供被配置为执行上述方法中的一个或多个的添加剂制造装置。

公开(公告)号：US20150156470A1

公开(公告)日：2015-06-04

申请号：US14613924

申请日：2015-02-04

Applicant: Massachusetts Institute of Technology

Inventor： Piotr Krzysztof Didyk ,  Song-Pei Du ,  Frederic Durand ,  Wojciech Matusik

IPC: H04N13/00 ,  H04N13/04

CPC classification number: H04N13/122 ,  H04N13/302 ,  H04N13/349

Abstract: Automultiscopic displays enable glasses-free 3D viewing by providing both binocular and motion parallax. Within the display field of view, different images are observed depending on the viewing direction. When moving outside the field of view, the observed images may repeat. Light fields produced by lenticular and parallax-barrier automultiscopic displays may have repetitive structure with significant discontinuities between the fields of view. This repetitive structure induces visual artifacts in the form of view discontinuities, depth reversals, and extensive disparities. To overcome this problem, a method modifies the presented light field image content and makes it more repetitive. In the method, a light field is refined using global and local shearing and then the repeating fragments are stitched. The method reduces the discontinuities in the displayed light field and leads to visual quality improvements. Benefits of the method are shown using an automultiscopic display with a parallax barrier and lenticular prints.

Abstract translation: 自动显示显示器通过提供双目和运动视差来实现无眼镜3D观看。 在显示视野内，根据观察方向观察不同的图像。 当移动到视野外时，观察到的图像可能会重复。 由透镜和视差屏障自动显微镜显示器产生的光场可能具有在视场之间具有显着不连续性的重复结构。 这种重复结构以视图不连续性，深度反转和广泛的差异的形式引起视觉伪影。 为了克服这个问题，一种方法修改了所呈现的光场图像内容并使其更重复。 在该方法中，使用全局和局部剪切来改进光场，然后缝合重复的片段。 该方法减少显示的光场中的不连续性，并导致视觉质量的改善。 使用具有视差屏障和透镜状印刷的自动显微镜显示该方法的优点。

公开(公告)号：US20140324204A1

公开(公告)日：2014-10-30

申请号：US14256894

申请日：2014-04-18

Applicant: Massachusetts Institute of Technology

Inventor： Kiril Vidimce ,  Wojciech Matusik

IPC: B29C67/00 ,  G06F17/50

CPC classification number: B29C67/0088 ,  B29C64/386 ,  B33Y50/00 ,  G06F17/50 ,  G06T11/40 ,  G06T17/00 ,  G06T17/20

Abstract: A programmable pipeline for synthesis of multi-material 3D printed objects supports procedural evaluation of geometric detail and material composition, using program modules allowing models to be specified easily and efficiently. A streaming architecture enables only a small fraction of the final volume to be stored in memory. Output is fed to the printer with little startup delay. A variety of multi-material objects are described. Procedural control over surface and volume stages as well as dithering is provided, together or independent of each other.

Abstract translation: 用于合成多材料3D打印对象的可编程管道支持几何细节和材料组成的程序评估，使用程序模块，允许轻松高效地指定模型。 流式架构只能将最终卷的一小部分存储在内存中。 输出以很少的启动延迟被馈送到打印机。 描述了各种多材料物体。 提供表面和体积级以及抖动的程序控制，彼此或彼此独立。