Super-resolution face image by using reference facial images with HIME

Super-resolution face image by using reference facial images with HIME

HIME: Efficient Headshot Image Super-Resolution with Multiple Exemplars
arXiv paper abstract https://arxiv.org/abs/2203.14863v1
arXiv PDF paper https://arxiv.org/pdf/2203.14863v1.pdf

A promising direction for recovering the lost information in low-resolution headshot images is utilizing a set of high-resolution exemplars from the same identity.

Complementary images in the reference set can improve the generated headshot … However … quality and alignment of each exemplar cannot be guaranteed.

Using low-quality and mismatched images as references will impair the output results.

… propose an efficient Headshot Image Super-Resolution with Multiple Exemplars network (HIME) method.

… network can effectively handle the misalignment between the input and the reference without requiring facial priors and learn the aggregated reference set representation in an end-to-end manner.

… demonstrate … framework not only has significantly fewer computation … but also achieves better qualitative and quantitative performance.

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

LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b

Photo by twentyonekoalas on Unsplash