Patents by Inventor Cihui Pan
Cihui Pan has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11721006Abstract: A method for generating an image of a scene with a corresponding depth map is disclosed herein. The method comprises collecting a plurality of copies of a two-dimensional image of the scene, generating an intermediate image by concatenating the plurality of copies of the two-dimensional image along a first direction, generating an intermediate depth map corresponding to the intermediate image by applying a neural network to the intermediate image, and generating, from the intermediate image and the intermediate depth map, the image of the scene with the corresponding depth map.Type: GrantFiled: June 3, 2021Date of Patent: August 8, 2023Assignee: Realsee (Beijing) Technology Co., Ltd.Inventors: Wenbo Shi, Xiaodong Gu, Cihui Pan, Chenglin Liu, Mingyuan Wang, Yonglin Yang
-
Patent number: 11620730Abstract: A method for combining multiple images is disclosed herein. A target mapping matrix is determined based on a first image and a second image. The target mapping matrix is associated with a target correspondence between the first image and the second image. The first image and the second image are combined into a combined image based on the first target mapping matrix. The combined image is output by implementing the disclosed method.Type: GrantFiled: March 23, 2021Date of Patent: April 4, 2023Assignee: Realsee (Beijing) Technology Co., Ltd.Inventors: Tong Rao, Cihui Pan, Mingyuan Wang, Xiaodong Gu, Chenglin Liu
-
Publication number: 20230035477Abstract: A method includes obtaining a color image and a first depth image; determining a target area of the first depth image, the target area of the first depth image having a first set of pixels with a first set of depth values; based on comparing an accuracy of the first set of depth values with a preset accuracy threshold: determining a target area of the color image that corresponds to the target area of the first depth image; determining, based on the target area of the color image, a second set of pixels with a second set of depth values for the target area of the first depth image; generating a second depth image that replaces the first set of pixels of the first depth image with the second set of pixels with the second set of depth values; outputting the second depth image as a three dimensional image.Type: ApplicationFiled: June 27, 2022Publication date: February 2, 2023Inventors: Xiaodong GU, Cihui PAN
-
Publication number: 20220138364Abstract: Systems and methods for generating a furnishing plan for a property are disclosed. An exemplary system includes a communication interface configured to receive a floor plan of the room and a resident profile. The system further includes at least one processor configured to determine a functionality of the room based at least partially on the resident profile and obtain a set of candidate furnishing items for the room based on the functionality of the room. The at least one processor is further configured to sequentially add furnishing items selected from the set of candidate furnishing items in the placement item set, where the furnishing items added in the furnishing plan collectively meet a predetermined area occupation threshold associated with the floor plan. The at least one processor is also configured to generating the furnishing plan based on the placement item set.Type: ApplicationFiled: September 30, 2021Publication date: May 5, 2022Applicant: Ke.com (Beijing) Technology Co., Ltd.Inventors: Mingzhe TIAN, Cihui PAN, Yilang HU, Linyuan LI, Shen ZHANG
-
Publication number: 20210365603Abstract: Systems and methods for generating a furnishing plan for a property are disclosed. An exemplary system includes a communication interface configured to receive a floor plan of the property, at least one candidate furnishing item to be placed in the property and attributes of the candidate furnishing item, and a first neural network model. The system further includes at least one processor configured to generate a mask based on the floor plan of the property and the attributes of the candidate furnishing item and generate proposals for placing the candidate furnishing item in the property based on the mask and the attributes of the candidate furnishing item. The at least one processor is further configured to determine a probability for each proposal using the first neural network model. The first neural network model is trained with a position query algorithm; select one or more proposals having the highest probabilities.Type: ApplicationFiled: May 18, 2021Publication date: November 25, 2021Applicant: Ke.com (Beijing) Technology Co., Ltd.Inventors: Xiaodong GU, Cihui PAN, Chenglin Liu, Yan ZHOU
-
Publication number: 20210295467Abstract: A method for combining multiple images is disclosed herein. A target mapping matrix is determined based on a first image and a second image. The target mapping matrix is associated with a target correspondence between the first image and the second image. The first image and the second image are combined into a combined image based on the first target mapping matrix. The combined image is output by implementing the disclosed method.Type: ApplicationFiled: March 23, 2021Publication date: September 23, 2021Inventors: Tong Rao, Cihui Pan, Mingyuan Wang, Xiaodong Gu, Chenglin Liu
-
Publication number: 20210287351Abstract: A method for generating an image of a scene with a corresponding depth map is disclosed herein. The method comprises collecting a plurality of copies of a two-dimensional image of the scene, generating an intermediate image by concatenating the plurality of copies of the two-dimensional image along a first direction, generating an intermediate depth map corresponding to the intermediate image by applying a neural network to the intermediate image, and generating, from the intermediate image and the intermediate depth map, the image of the scene with the corresponding depth map.Type: ApplicationFiled: June 3, 2021Publication date: September 16, 2021Inventors: Wenbo Shi, Xiaodong Gu, Cihui Pan, Chenglin Liu, Mingyuan Wang, Yonglin Yang
-
Patent number: 11055835Abstract: A method for generating an image of a scene with a corresponding depth map is disclosed herein. The method comprises collecting a plurality of copies of a two-dimensional image of the scene, generating an intermediate image by concatenating the plurality of copies of the two-dimensional image along a first direction, generating an intermediate depth map corresponding to the intermediate image by applying a neural network to the intermediate image, and generating, from the intermediate image and the intermediate depth map, the image of the scene with the corresponding depth map.Type: GrantFiled: September 25, 2020Date of Patent: July 6, 2021Assignee: Ke.com (Beijing) Technology, Co., Ltd.Inventors: Wenbo Shi, Xiaodong Gu, Cihui Pan, Chenglin Liu, Mingyuan Wang, Yonglin Yang
-
Publication number: 20210150683Abstract: A method for generating an image of a scene with a corresponding depth map is disclosed herein. The method comprises collecting a plurality of copies of a two-dimensional image of the scene, generating an intermediate image by concatenating the plurality of copies of the two-dimensional image along a first direction, generating an intermediate depth map corresponding to the intermediate image by applying a neural network to the intermediate image, and generating, from the intermediate image and the intermediate depth map, the image of the scene with the corresponding depth map.Type: ApplicationFiled: September 25, 2020Publication date: May 20, 2021Inventors: Wenbo Shi, Xiaodong Gu, Cihui Pan, Chenglin Liu, Mingyuan Wang, Yonglin Yang
-
Patent number: 11004261Abstract: A method of generating a three-dimensional point cloud includes obtaining a plurality of image data sources through a plurality of sensors, and performing fusion processing according to the plurality of image data sources to obtain the three-dimensional point cloud.Type: GrantFiled: May 15, 2019Date of Patent: May 11, 2021Assignee: SZ DJI TECHNOLOGY CO., LTD.Inventors: Yao Yao, Kaiyong Zhao, Shizhen Zheng, Cihui Pan
-
Publication number: 20190370989Abstract: A method for 3-dimensional point cloud reconstruction includes obtaining image data in a current view angle, and generating a target voxel of a target object in the current view angle according to the image data. The target voxel contains depth information. The method further includes, if a value of the depth information of the target voxel is not within a preset range, discarding the target voxel and, if the value of the depth information of the target voxel is within the preset range, fusing the target voxel with one or more stored voxels.Type: ApplicationFiled: August 15, 2019Publication date: December 5, 2019Inventors: Kaiyong ZHAO, Cihui PAN, Yuewen MA, Yao YAO
-
Patent number: 10447992Abstract: The present disclosure discloses a method and a system for image processing. The method includes: obtaining images of a target environment captured by a robot in a preset movement trajectory according to a predefined condition; combining every two of the images having a same region into a corresponding image pair based on an initial position estimation of each of the images; producing an image seed based on the image pair; performing position optimization on the image seed; producing an image subset based on the image seed after the position optimization; and performing position optimization on the image subset based on the image seeds in the image subset. It can effectively reduce the computational complexity of image matching, reduce the calculation time, and improve the accuracy of image processing.Type: GrantFiled: August 17, 2018Date of Patent: October 15, 2019Assignee: UBTECH ROBOTICS CORPInventors: Youjun Xiong, Cihui Pan, Shengqi Tan, Xianji Wang, Jianxin Pang
-
Publication number: 20190266792Abstract: A method of generating a three-dimensional point cloud includes obtaining a plurality of image data sources through a plurality of sensors, and performing fusion processing according to the plurality of image data sources to obtain the three-dimensional point cloud.Type: ApplicationFiled: May 15, 2019Publication date: August 29, 2019Inventors: Yao YAO, Kaiyong ZHAO, Shizhen ZHENG, Cihui PAN
-
Publication number: 20190206117Abstract: The present disclosure provides an image processing method, an intelligent terminal, and a storage device. The image processing method may include: obtaining an original image, and obtaining mask information of a target object from the original image, wherein the mask information includes classification information for foreground and background of the target object; denoising the original image to obtain a denoised image of the original image; and obtaining a target image from the denoised image according to the mask information of the target object. The present disclosure can improve the quality of the image by denoising the original image, and the obtained target image can be a minimum-sized image including all the information of the target object. Because the size of the image is reduced without losing valid information, the calculation amount of the 3D synthesis can be greatly reduced.Type: ApplicationFiled: December 25, 2018Publication date: July 4, 2019Inventors: Youjun XIONG, Shengqi Tan, Cihui Pan, Xianji Wang, Jianxin Pang
-
Publication number: 20190197735Abstract: The present disclosure provides a method and an apparatus for image processing, and a robot using the same. The method includes: obtaining a depth map and a color map of a target object in a predetermined scene; filtering the depth map based on the color map to obtain a first depth filter map; detecting pixel values of pixels in the first depth filter map to obtain one or more first pixels, and forming a black dot cavity area based on the one or more first pixels; re-assigning a depth value of each of the one or more first pixels in the black dot cavity area according to a preset rule to obtain the depth map after repair; and filtering the depth map after repair to obtain a second depth filter map. The present disclosure is capable of improving the quality of the depth map.Type: ApplicationFiled: November 30, 2018Publication date: June 27, 2019Inventors: Youjun Xiong, Shengqi Tan, Cihui Pan, Xianji Wang, Jianxin Pang