Image processing method and device, storage medium and electronic equipment
By introducing a second encoder into the image processing model and using the first loss function for training constraints, the problem of the complexity of the low-quality image restoration process is solved, achieving efficient image sharpening and reducing model complexity, making it suitable for mobile terminals.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING XIAOMI MOBILE SOFTWARE CO LTD
- Filing Date
- 2021-11-30
- Publication Date
- 2026-07-21
AI Technical Summary
The existing technology for restoring low-quality blurry images to high-quality clear images is complex and inefficient, and is particularly difficult to deploy on mobile terminals.
A target image processing model is adopted, including a first encoder and a first decoder, and a second encoder is introduced. The degree of difference between the encoded vector and the encoded vector is calculated through a first loss function. The trained first encoder has the ability to reverse image mapping and remove blur degradation. The second encoder is used for constraints during model training, and the second encoder is removed during application to reduce complexity.
The training process improves the encoder's inverse mapping and blur removal capabilities while reducing the complexity of the target image processing model, making it suitable for deployment on mobile devices.
Smart Images

Figure CN116206168B_ABST