US 11,995,703 B2
Image-to-image translation using unpaired data for supervised learning
Eric Elmoznino, Toronto (CA); Irina Kezele, Toronto (CA); and Parham Aarabi, Richmond Hill (CA)
Assigned to L'OREAL, Paris (FR)
Filed by L'OREAL, Paris (FR)
Filed on Jan. 27, 2023, as Appl. No. 18/102,139.
Application 18/102,139 is a continuation of application No. 17/096,774, filed on Nov. 12, 2020, granted, now 11,615,516.
Claims priority of provisional application 62/935,715, filed on Nov. 15, 2019.
Prior Publication US 2023/0169571 A1, Jun. 1, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 5/50 (2006.01); G06F 18/214 (2023.01); G06N 20/00 (2019.01); G06Q 30/0601 (2023.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/778 (2022.01)
CPC G06Q 30/0631 (2013.01) [G06F 18/214 (2023.01); G06N 20/00 (2019.01); G06T 5/50 (2013.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/7788 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
training a run-time model using supervised learning techniques where synthetic data generated from an image translation model provide ground truths for the training of the run-time model, the run-time model trained to translate images from a first domain to a second domain and the run-time model comprising a compact and fast model in comparison to the image translation model.