CAIR: Fast and Lightweight Multi-Scale Color Attention Network for Instagram Filter Removal
Woon-Ha Yeo, Wang-Taek Oh, Kyung-Su Kang, Young-Il Kim, Han-Cheol Ryu

TL;DR
CAIR is a novel, fast, and lightweight multi-scale color attention network designed for effective Instagram filter removal, significantly outperforming existing methods in speed and efficiency while maintaining high restoration quality.
Contribution
The paper introduces CAIR, a new network combining multi-scale features and color attention, achieving superior speed and lightweight performance for Instagram filter removal.
Findings
CAIR is 11 times faster than existing methods.
CAIR is 2.4 times lighter in model size.
CAIR exceeds 3.69 dB PSNR on IFFI dataset.
Abstract
Image restoration is an important and challenging task in computer vision. Reverting a filtered image to its original image is helpful in various computer vision tasks. We employ a nonlinear activation function free network (NAFNet) for a fast and lightweight model and add a color attention module that extracts useful color information for better accuracy. We propose an accurate, fast, lightweight network with multi-scale and color attention for Instagram filter removal (CAIR). Experiment results show that the proposed CAIR outperforms existing Instagram filter removal networks in fast and lightweight ways, about 11 faster and 2.4 lighter while exceeding 3.69 dB PSNR on IFFI dataset. CAIR can successfully remove the Instagram filter with high quality and restore color information in qualitative results. The source code and pretrained weights are available at…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage Enhancement Techniques · Image and Signal Denoising Methods · Advanced Image Fusion Techniques
