公开(公告)号：US20230035671A1

公开(公告)日：2023-02-02

申请号：US17376027

申请日：2021-07-14

Applicant: Black Sesame Technologies Inc.

Inventor： Tiecheng Wu ,  Bo Li

IPC: G06T7/55 ,  G06T5/00 ,  G06N20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a depth image, comprising obtaining data representing a first image generated by a first sensor and a second image generated by a second sensor, wherein each of the first and second images includes a plurality of pixels; determining, for each pixel of the plurality of pixels included in the first image, whether the pixel is a boundary pixel associated with a boundary of an object that is represented in the first image; determining, from a plurality of candidate penalty values and for each pixel in the first image, an optimized penalty value for the pixel; generating an optimized cost function for the first image based on the optimized penalty values for the plurality of pixels; and generating a depth image for the first image based on the optimized cost function.

公开(公告)号：US12190535B2

公开(公告)日：2025-01-07

申请号：US17688694

申请日：2022-03-07

Applicant: Black Sesame Technologies Inc.

Inventor： Tiecheng Wu ,  Bo Li

IPC: G06T5/50 ,  G06T7/13 ,  G06T7/50

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a machine learning model configured to generate a predicted depth image, comprising receiving data representing training samples that include a plurality of image pairs, each image pair includes a target image and a reference image both capturing a particular scene from different orientations; for each of the plurality of image pairs, generating a compressed cost volume for the image pair; providing the compressed cost volume as an input to the machine learning model; generating, using the machine learning model, output data representing a predicted disparity map for the compressed cost volume; and generating a total loss using the predicted disparity map for the compressed cost volume, the total loss includes a boundary loss, an occlusion loss, and a transfer loss; and updating the plurality of parameters of the machine learning model by minimizing the total losses.

公开(公告)号：US20230281843A1

公开(公告)日：2023-09-07

申请号：US17688694

申请日：2022-03-07

Applicant: Black Sesame Technologies Inc.

Inventor： Tiecheng Wu ,  Bo Li

IPC: G06T7/50 ,  G06T7/13

CPC classification number: G06T7/50 ,  G06T7/13 ,  G06T2207/20081

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a machine learning model configured to generate a predicted depth image, comprising receiving data representing training samples that include a plurality of image pairs, each image pair includes a target image and a reference image both capturing a particular scene from different orientations; for each of the plurality of image pairs, generating a compressed cost volume for the image pair; providing the compressed cost volume as an input to the machine learning model; generating, using the machine learning model, output data representing a predicted disparity map for the compressed cost volume; and generating a total loss using the predicted disparity map for the compressed cost volume, the total loss includes a boundary loss, an occlusion loss, and a transfer loss; and updating the plurality of parameters of the machine learning model by minimizing the total losses.

公开(公告)号：US20240153099A1

公开(公告)日：2024-05-09

申请号：US17978430

申请日：2022-11-01

Applicant: Black Sesame Technologies Inc.

Inventor： Xibeijia Guan ,  Tiecheng Wu ,  Bo Li

IPC: G06T7/194 ,  G06V10/25 ,  G06V10/26

CPC classification number: G06T7/194 ,  G06V10/25 ,  G06V10/267 ,  G06T2207/20132

Abstract: The invention discloses a system for image segmentation for detecting an object. More particularly, the system performs two-stage segmentation on the object in the image to generate an enhanced image. The first stage is the object detection, followed by a second stage including segmentation. The invention segments the object from a background of the image to create an enhanced image.

公开(公告)号：US11961249B2

公开(公告)日：2024-04-16

申请号：US17376027

申请日：2021-07-14

Applicant: Black Sesame Technologies Inc.

Inventor： Tiecheng Wu ,  Bo Li

IPC: G06T7/55 ,  G06N20/00 ,  G06T5/70

CPC classification number: G06T7/55 ,  G06N20/00 ,  G06T5/70 ,  G06T2207/20081

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a depth image, comprising obtaining data representing a first image generated by a first sensor and a second image generated by a second sensor, wherein each of the first and second images includes a plurality of pixels; determining, for each pixel of the plurality of pixels included in the first image, whether the pixel is a boundary pixel associated with a boundary of an object that is represented in the first image; determining, from a plurality of candidate penalty values and for each pixel in the first image, an optimized penalty value for the pixel; generating an optimized cost function for the first image based on the optimized penalty values for the plurality of pixels; and generating a depth image for the first image based on the optimized cost function.