Private and Decentralized 3D from Crowd Sourced Image Data
Dave, Akshat Raskar, Ramash Singh, Abhishek Tasneem, Zaid Tiwary, Kushagra Veeraraghavan, Ashok Vepakomma, Praneeth
Dave, Akshat
Raskar, Ramash
Singh, Abhishek
Tasneem, Zaid
Tiwary, Kushagra
Veeraraghavan, Ashok
Vepakomma, Praneeth
Supervisor
Department
Machine Learning
Embargo End Date
Type
Patent
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
In one aspect, a method for rendering of a 3D aggregate image from crowd sourced image data is provided. The method includes receiving, at a server, from each of a plurality of user devices, user global multi-layer perceptron (MLP) weights generated from one or more images of a shared scene. The user global MLP weights are generated so as to not include personal content of a user. The method also includes aggregating the user global MLP weights using secure multi-party computation (SMPC) to further ensure exclusion of personal content. The method also includes sending, from the server to the plurality of user devices, updated weights, wherein the updated weights comprise aggregated global MLP weights. The user devices may then use the updated weights to further help in the implicit separation of personal and global content while retraining of their respective weights on local image data.
Citation
“US20250336144A1 - Private and Decentralized 3D from Crowd Sourced Image Data - Google Patents.” [Online]. Available: https://patents.google.com/patent/US20250336144A1/en
Source
US Patent App
Conference
Keywords
Subjects
Source
Publisher
Google Patent