Enhance dim images better and simpler using imperfectly aligned images with CIDN


Enhance dim images better and simpler using imperfectly aligned images with CIDN

Enhancing Low-Light Images in Real World via Cross-Image Disentanglement
arXiv paper abstract https://arxiv.org/abs/2201.03145v1
arXiv PDF paper https://arxiv.org/pdf/2201.03145v1.pdf

Images captured in the low-light … suffer from low visibility and … artifacts, e.g., real noise.

Existing supervised enlightening algorithms require a large set of pixel-aligned training image pairs, which are hard to prepare

… instead of using perfectly aligned images for training, … creatively employ the misaligned real-world images as the guidance

… propose a Cross-Image Disentanglement Network (CIDN) to separately extract cross-image brightness and image-specific content features from low/normal-light images.

… CIDN can simultaneously correct the brightness and suppress image artifacts in the feature domain, which largely increases the robustness to the pixel shifts.

… model achieves state-of-the-art performances on both the newly proposed dataset and other popular low-light datasets.

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 Rémi Thorel on Unsplash



AI News Clips by Morris Lee: News to help your R&D

A computer vision consultant in artificial intelligence and related hitech technologies 37+ years. Am innovator with 66+ patents and ready to help a firm's R&D.