Spatially Variant Laplacian Pyramids for Multi-Frame Exposure Fusion
This work addresses artifact-free image blending for applications like HDR imaging, but it is incremental as it modifies an existing method for a known bottleneck.
The paper tackled the problem of blending images with large intensity variations, such as in exposure fusion, by proposing a spatially varying Laplacian Pyramid Blending method that dynamically adjusts blending levels based on local intensity variation, resulting in outperforming state-of-the-art methods on an HDR dataset with improvements in details, halos, and dark halos, and achieving better MEF-SSIM scores.
Laplacian Pyramid Blending is a commonly used method for several seamless image blending tasks. While the method works well for images with comparable intensity levels, it is often unable to produce artifact free images for applications which handle images with large intensity variation such as exposure fusion. This paper proposes a spatially varying Laplacian Pyramid Blending to blend images with large intensity differences. The proposed method dynamically alters the blending levels during the final stage of Pyramid Reconstruction based on the amount of local intensity variation. The proposed algorithm out performs state-of-the-art methods for image blending both qualitatively as well as quantitatively on publicly available High Dynamic Range (HDR) imaging dataset. Qualitative improvements are demonstrated in terms of details, halos and dark halos. For quantitative comparison, the no-reference perceptual metric MEF-SSIM was used.