Image Blending Algorithm with Automatic Mask Generation
This addresses efficiency and quality issues in image blending for content creators, though it appears incremental as it builds on existing techniques.
The paper tackles the problems of manual mask creation and brightness distortion/low resolution in image blending by proposing a method with automatic mask generation using semantic object detection and segmentation, combined with a new saturation loss and two-stage PAN iteration. Results show it outperforms classical algorithms on metrics like PSNR and SSIM.
In recent years, image blending has gained popularity for its ability to create visually stunning content. However, the current image blending algorithms mainly have the following problems: manually creating image blending masks requires a lot of manpower and material resources; image blending algorithms cannot effectively solve the problems of brightness distortion and low resolution. To this end, we propose a new image blending method with automatic mask generation: it combines semantic object detection and segmentation with mask generation to achieve deep blended images based on our proposed new saturation loss and two-stage iteration of the PAN algorithm to fix brightness distortion and low-resolution issues. Results on publicly available datasets show that our method outperforms other classical image blending algorithms on various performance metrics, including PSNR and SSIM.