公开(公告)号：US20240296576A1

公开(公告)日：2024-09-05

申请号：US18447709

申请日：2023-08-10

Applicant: QUALCOMM Incorporated

Inventor： Mohsen Ghafoorian ,  Georgi Dikov ,  Xuepeng Shi ,  Jihong Ju ,  Gerhard Reitmayr

IPC: G06T7/55

CPC classification number: G06T7/55 ,  G06T2207/20081 ,  G06T2207/20224

Abstract: This disclosure provides systems, methods, and devices for image signal processing that support artificial intelligence (AI)-based processing of image data for reconstructing 3D worlds. In a first aspect, a method of image processing includes receiving a plurality of image frames representing a scene; determining a first depth prediction for the scene based on the plurality of image frames; determining a reconstructed mesh from the plurality of image frames; determining a second depth prediction for the scene based on the reconstructed mesh; and determining a third depth prediction based on the first depth prediction and the second depth prediction. Other aspects and features are also claimed and described.

公开(公告)号：US20250086946A1

公开(公告)日：2025-03-13

申请号：US18463756

申请日：2023-09-08

Applicant: QUALCOMM Incorporated

Inventor： Debasmit Das ,  Mohsen Ghafoorian ,  Oleksandr Bailo ,  Yu Fu ,  Hyojin Park ,  Shubhankar Mangesh Borse ,  Fatih Murat Porikli

IPC: G06V10/776 ,  G06T7/11 ,  G06T7/174 ,  G06T7/80 ,  G06V10/74 ,  G06V10/774

Abstract: A system stores first and second images generated by first and second cameras; applies a segmentation model to the first image to generate a first segmentation mask identifying object instances; applies the segmentation model to the second image to generate a second segmentation mask identifying the object instances; projects the first segmentation mask to a viewpoint of the second camera to generate a first projected segmentation mask; converts the first projected segmentation mask and the second segmentation mask to first and second semantic masks, respectively; and computes a first similarity value based on the first and second semantic masks. This may be repeated exchanging the first and second images to compute a second similarity value. The system determines a loss value based on the first similarity value and the second similarity value and trains the segmentation model based on the loss value.