-
1.发明授权公开(公告)号：US10657664B2
公开(公告)日：2020-05-19
申请号：US16004430
申请日：2018-06-11
Applicant: Jingyi Yu
Inventor： Jingyi Yu
IPC: G06T7/50 , G06T15/06 , H04N13/111 , H04N13/243 , H04N13/254 , H04N13/246 , H04N13/271 , G06T7/80 , G06T15/20
Abstract: A method and system for capturing images and depth for image-based rendering. Capture is made by a multi-camera configuration using a combination of image and depth cameras. Rendering utilizes scene geometry derived from image and depth data.
-
公开(公告)号：US07218792B2
公开(公告)日：2007-05-15
申请号：US10392067
申请日：2003-03-19
Applicant: Ramesh Raskar , Jingyi Yu
Inventor： Ramesh Raskar , Jingyi Yu
CPC classification number: H04N5/2625 , G06T15/02 , H04N5/2256
Abstract: A method generates a stylized image. First, a set of images is acquired of a scene. Each image is acquired under a different lighting condition. Silhouette edges are detected in the set of images. Texture regions are identified in the set of images according to the silhouette edges, and an output image is generated from a combination of the set of images wherein the silhouette edges and the texture regions are altered so as to enhance or de-emphasize selected details.
Abstract translation: 方法生成风格化图像。 首先，获取一组场景的图像。 每个图像在不同的照明条件下被采集。 在图像集中检测到轮廓边缘。 根据轮廓边缘在图像组中识别纹理区域，并且从图像组合的组合生成输出图像，其中轮廓边缘和纹理区域被改变以增强或去强调所选择的细节。
-
公开(公告)号：US20160253824A1
公开(公告)日：2016-09-01
申请号：US15026768
申请日：2014-10-03
CPC classification number: G06T11/003 , G06T5/001 , H04N5/222 , H04N5/2253 , H04N5/2254 , H04N5/23209 , H04N13/204
Abstract: Multi-perspective cameras, systems and methods for reconstructing a scene are provided. Light representing a scene is directed through a lens module coupled to an imaging sensor. The lens module includes: first and second cylindrical lenses positioned along an optical axis of the imaging sensor, and first and second slit-shaped apertures disposed on the respective first and second cylindrical lenses. A cylindrical axis of the second cylindrical lens is arranged at an angle away from parallel with respect to a cylindrical axis of the first cylindrical lens. The light directed through the lens module is captured by the imaging sensor to form at least one multi-perspective image. The at least one multi-perspective image is processed to determine a reconstruction characteristic of the scene.
Abstract translation: 提供了多视角相机，用于重建场景的系统和方法。 表示场景的光被引导通过耦合到成像传感器的透镜模块。 透镜模块包括：沿着成像传感器的光轴定位的第一和第二柱面透镜，以及设置在相应的第一和第二柱面透镜上的第一和第二狭缝状孔。 第二柱面透镜的圆柱轴线相对于第一柱面透镜的圆柱轴线成平行的角度布置。 通过透镜模块引导的光被成像传感器捕获以形成至少一个多视角图像。 处理至少一个多视角图像以确定场景的重建特性。
-
公开(公告)号：US11354840B2
公开(公告)日：2022-06-07
申请号：US16823328
申请日：2020-03-19
Applicant: Jingyi Yu
Inventor： Jingyi Yu
Abstract: A method and system of using multiple image cameras or multiple image and depth cameras to capture a target object. Geometry and texture are reconstructed using captured images and depth images. New images are rendered using geometry based rendering methods or image based rendering methods.
-
公开(公告)号：US20200219301A1
公开(公告)日：2020-07-09
申请号：US16823328
申请日：2020-03-19
Applicant: Jingyi YU
Inventor： Jingyi YU
Abstract: A method and system of using multiple image cameras or multiple image and depth cameras to capture a target object. Geometry and texture are reconstructed using captured images and depth images. New images are rendered using geometry based rendering methods or image based rendering methods.
-
Patent Agency Ranking
公开(公告)号：US07206449B2
公开(公告)日：2007-04-17
申请号：US10391999
申请日：2003-03-19
Applicant: Ramesh Raskar , Jingyi Yu
Inventor： Ramesh Raskar , Jingyi Yu
CPC classification number: G06T5/50 , G06T11/00 , G06T2207/10152 , G06T2207/20192
Abstract: A method detects silhouette edges in images. An ambient image is acquired of a scene with ambient light. A set of illuminated images is also acquired of the scene. Each illuminated image is acquired with a different light source illuminating the scene. The ambient image is combined with the set of illuminated to detect cast shadows, and silhouette edge pixels are located from the cast shadows.
Abstract translation: 一种方法检测图像中的轮廓边缘。 用环境光获取场景的环境图像。 还拍摄了一组照明图像。 用照亮场景的不同光源获取每个照明图像。 环境图像与照明的组合组合以检测投射阴影，并且轮廓边缘像素位于投射阴影处。
-
公开(公告)号：US07102638B2
公开(公告)日：2006-09-05
申请号：US10392000
申请日：2003-03-19
Applicant: Ramesh Raskar , Jingyi Yu , Adrian Ilie
Inventor： Ramesh Raskar , Jingyi Yu , Adrian Ilie
IPC: G09G5/02
Abstract: A method generates an image with de-emphasized textures. Each pixel in the image is classified as either a silhouette edge pixel, a texture edge pixels, or a featureless pixel. A mask image M(x, y) is generated, wherein an intensity of a given pixel (x, y) in the mask image M(x, y) is zero if the pixel (x, y) is classified as the texture edge pixel, is d(x, y) if the pixel (x, y) is classified as the featureless pixel, and is one if the pixel (x, y) is classified as the silhouette edge pixel. An intensity gradient ∇I(x, y) is determined in the masked image, and the intensity gradients in the masked image are integrated according to G(x, y)=∇I(x, y). M(x, y). Then, an output image I′ is generated by minimizing |∇I′−G|, and normalizing the intensities in the output image I′.
Abstract translation: 方法生成具有去加重纹理的图像。 图像中的每个像素被分类为轮廓边缘像素，纹理边缘像素或无特征像素。 生成掩模图像M（x，y），其中如果像素（x，y）被分类为纹理边缘，则掩模图像M（x，y）中的给定像素（x，y）的强度为零 像素，如果像素（x，y）被分类为无特征像素，则为d（x，y），并且如果像素（x，y）被分类为轮廓边缘像素则为像素（x，y）。 在掩蔽图像中确定强度梯度∇I（x，y），并根据G（x，y）=∇I（x，y）将屏蔽图像中的强度梯度积分。 M（x，y）。 然后，通过最小化|∇I'-G |并且使输出图像I'的强度标准化来生成输出图像I'。
-
公开(公告)号：US20180293774A1
公开(公告)日：2018-10-11
申请号：US16004434
申请日：2018-06-11
Applicant: Jingyi YU
Inventor： Jingyi YU
Abstract: A method and system of using multiple image cameras or multiple image and depth cameras to capture a target object. Geometry and texture are reconstructed using captured images and depth images. New images are rendered using geometry based rendering methods or image based rendering methods.
-
公开(公告)号：US20160330432A1
公开(公告)日：2016-11-10
申请号：US15107661
申请日：2014-12-23
Applicant: Jingyi Yu , Xinqing Guo , Zhan Yu
Inventor： Jingyi Yu , Xinqing Guo , Zhan Yu
CPC classification number: H04N13/207 , G02B3/005 , G06T15/205 , G06T2200/04 , G06T2200/28 , G06T2207/10012 , H04N5/2254 , H04N13/111 , H04N13/128 , H04N13/232 , H04N13/305
Abstract: Methods and systems for generating three-dimensional (3D) images, 3D light field (LF) cameras and 3D photographs are provided. Light representing a scene is directed through a lens module coupled to an imaging sensor. The lens module includes: a surface having a slit-shaped aperture and a cylindrical lens array positioned along an optical axis of the imaging sensor. A longitudinal direction of the slit-shaped aperture is arranged orthogonal to a cylindrical axis of the cylindrical lens array. The light directed through the lens module is captured by the imaging sensor to form a 3D LF image. A 3D photograph includes a 3D LF printed image of the scene and a cylindrical lens array disposed on the printed image, such that the combination of 3D LF printed image and the cylindrical lens array forms a 3D stereoscopic image.
Abstract translation: 提供了用于生成三维（3D）图像，3D光场（LF）照相机和3D照片的方法和系统。 表示场景的光被引导通过耦合到成像传感器的透镜模块。 透镜模块包括：具有狭缝形孔的表面和沿成像传感器的光轴定位的柱面透镜阵列。 狭缝状孔的长度方向与柱面透镜阵列的圆筒轴正交地配置。 通过透镜模块引导的光被成像传感器捕获以形成3D LF图像。 3D照片包括场景的3D LF打印图像和设置在打印图像上的柱面透镜阵列，使得3D LF打印图像和柱面透镜阵列的组合形成3D立体图像。
-
公开(公告)号：US10789752B2
公开(公告)日：2020-09-29
申请号：US16004434
申请日：2018-06-11
Applicant: Jingyi Yu
Inventor： Jingyi Yu
Abstract: A method and system of using multiple image cameras or multiple image and depth cameras to capture a target object. Geometry and texture are reconstructed using captured images and depth images. New images are rendered using geometry based rendering methods or image based rendering methods.
-
-
-
-
-
-
-
-
-
Search Results
13
records
(took 0.012 seconds)
