Correcting over-exposed image by combining many images using texture
Correcting over-exposed image by combine many images using texture
Attention-Guided Progressive Neural Texture Fusion for High Dynamic Range Image Restoration
arXiv paper abstract https://arxiv.org/abs/2107.06211v1
arXiv PDF paper https://arxiv.org/pdf/2107.06211v1.pdf
High Dynamic Range (HDR) imaging via multi-exposure fusion is an important task for most modern imaging platforms.
... challenges remain over content association ambiguities caused by saturation, motion, and various artifacts ... such as ghosting, noise, and blur.
... propose an Attention-guided Progressive Neural Texture Fusion (APNT-Fusion) HDR restoration model
... establishes spatial correspondence between different exposures based on multi-scale VGG features
... motion attention module detects and suppresses the content discrepancies among the reference images
... validate that these novel modules work coherently under the same framework and outperform state-of-the-art methods.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments