The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Dec. 16, 2025

Filed:

Aug. 04, 2023
Applicant:

Naver Corporation, Gyeonggi-do, KR;

Inventors:

Romain Brégier, Grenoble, FR;

Yohann Cabon, Montbonnot-Saint-Martin, FR;

Thomas Lucas, Grenoble, FR;

Jérôme Revaud, Meylan, FR;

Philippe Weinzaepfel, Montonnot-Saint-Martin, FR;

Boris Chidlovskii, Meylan, FR;

Vincent Leroy, Laval, FR;

Leonid Antsfeld, Saint Ismier, FR;

Gabriela Csurka Khedari, Crolles, FR;

Assignee:

NAVER CORPORATION, Gyeonggi-Do, KR;

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06V 10/82 (2022.01); G06N 3/0455 (2023.01); G06N 3/088 (2023.01); G06T 7/70 (2017.01); G06V 10/44 (2022.01); G06V 10/774 (2022.01); G06V 10/776 (2022.01); G06V 10/80 (2022.01); G06V 10/96 (2022.01); G06V 20/64 (2022.01); G06V 40/10 (2022.01);
U.S. Cl.
CPC ...
G06V 10/82 (2022.01); G06N 3/0455 (2023.01); G06N 3/088 (2013.01); G06T 7/70 (2017.01); G06V 10/44 (2022.01); G06V 10/7753 (2022.01); G06V 10/776 (2022.01); G06V 10/80 (2022.01); G06V 10/96 (2022.01); G06V 20/64 (2022.01); G06V 40/10 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/30196 (2013.01);
Abstract

A method includes: performing unsupervised pre-training of a model, the model including and a decoder including: obtaining a first image and a second image under different conditions or from different viewpoints; encoding, by the encoder, the first image into a representation of the first image and the second image into a representation of the second image; transforming the representation of the first image into a transformed representation; decoding, by the decoder, the transformed representation into a reconstructed image, where the transforming of the representation of the first image and the decoding of the transformed representation is based on the representation of the first image and the representation of the second image; and adjusting one or more parameters of at least one of the encoder and the decoder based on minimizing a loss; and fine-tuning the model, initialized with a set of task specific encoder parameters, for a geometric vision task.


Find Patent Forward Citations

Loading…