Self-Supervised Learning for Real-World Super-Resolution from Dual and Multiple Zoomed Observations

arXiv:2405.02171v1 Announce Type: new
Abstract: In this paper, we consider two challenging issues in reference-based super-resolution (RefSR) for smartphone, (i) how to choose a proper reference image, and (ii) how to learn RefSR in a self-supervised manner. Particularly, we propose a novel self-supervised learning approach for real-world RefSR from observations at dual and multiple camera zooms. Firstly, considering the popularity of multiple cameras in modern smartphones, the more zoomed (telephoto) image can be naturally leveraged as the reference to guide …

arxiv cs.cv multiple resolution self-supervised learning supervised learning type world