Invention Grant
- Patent Title: Media enhancement using discriminative and generative models with feedback
-
Application No.: US17172744Application Date: 2021-02-10
-
Publication No.: US12136189B2Publication Date: 2024-11-05
- Inventor: Akhilesh Kumar , Zhe Lin , Baldo Faieta
- Applicant: ADOBE INC.
- Applicant Address: US CA San Jose
- Assignee: ADOBE INC.
- Current Assignee: ADOBE INC.
- Current Assignee Address: US CA San Jose
- Agency: F. CHAU & ASSOCIATES, LLC
- Main IPC: G06T7/00
- IPC: G06T7/00 ; G06F18/214 ; G06F18/2411 ; G06N3/04 ; G06T5/20

Abstract:
The present disclosure describes systems and methods for image enhancement. Embodiments of the present disclosure provide an image enhancement system with a feedback mechanism that provides quantifiable image enhancement information. An image enhancement system may include a discriminator network that determines the quality of the media object. In cases where the discriminator network determines that the media object has a low image quality score (e.g., an image quality score below a quality threshold), the image enhancement system may perform enhancement on the media object using an enhancement network (e.g., using an enhancement network that includes a generative neural network or a generative adversarial network (GAN) model). The discriminator network may then generate an enhancement score for the enhanced media object that may be provided to the user as a feedback mechanism (e.g., where the enhancement score generated by the discriminator network quantifies the enhancement performed by the enhancement network).
Public/Granted literature
- US20220253990A1 MEDIA ENHANCEMENT USING DISCRIMINATIVE AND GENERATIVE MODELS WITH FEEDBACK Public/Granted day:2022-08-11
Information query