图像生成方法、装置、设备及介质
By acquiring multiple frames of images and sensor data, performing feature extraction and motion field matrix estimation, the problem of poor image reconstruction quality in existing technologies is solved, and high-quality super-resolution image generation is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- VIVO MOBILE COMM CO LTD
- Filing Date
- 2022-09-19
- Publication Date
- 2026-07-17
AI Technical Summary
In existing technologies, image reconstruction methods based on super-resolution algorithms cannot effectively supplement image detail information, resulting in poor image quality and the generated image details not conforming to reality.
By acquiring multiple frames of raw images, depth maps, and motion sensor data, reference and non-reference images are determined, feature extraction and motion field matrix estimation are performed, and super-resolution reconstruction is carried out by combining motion sensor data and depth map feature maps to generate high-quality super-resolution images.
It improves the quality and efficiency of image reconstruction, ensuring that the generated image details match the real situation, and is suitable for various electronic devices.
Smart Images
Figure CN115423873B_ABST