Invention Grant
- Patent Title: Spatial metrics for denoising depth image data
-
Application No.: US17445825Application Date: 2021-08-24
-
Publication No.: US12045959B2Publication Date: 2024-07-23
- Inventor: Sergio Ortiz Egea , Augustine Cha
- Applicant: Microsoft Technology Licensing, LLC
- Applicant Address: US WA Redmond
- Assignee: Microsoft Technology Licensing, LLC
- Current Assignee: Microsoft Technology Licensing, LLC
- Current Assignee Address: US WA Redmond
- Agency: Alleman Hall & Tuttle LLP
- Main IPC: G06T5/70
- IPC: G06T5/70 ; G01S17/42 ; G01S17/894 ; G06T5/20 ; G06T7/11 ; G06T7/521

Abstract:
Examples are disclosed relating to performing denoising and adaptive precision control on time-of-flight sensor data using noise metrics. One example provides a computing system, comprising, a logic machine, and a storage machine holding instructions executable by the logic machine to obtain time-of-flight (ToF) image data comprising a plurality of pixels, for each pixel of the ToF image data, determine one or more noise metrics by applying a spatial kernel, segment the ToF image data based on the one or more noise metrics to obtain differently classified pixels, during a denoising phase, process pixels of a first classification differently than pixels of a second classification, after the denoising phase, determine a depth image, and output the depth image.
Public/Granted literature
- US20230081137A1 SPATIAL METRICS FOR DENOISING DEPTH IMAGE DATA Public/Granted day:2023-03-16
Information query