GIA-Net: Global Information Aware Network for Low-light Imaging
Zibo Meng, Runsheng Xu, Chiu Man Ho

TL;DR
GIA-Net introduces a global information aware module integrated into U-Nets to enhance low-light image quality, reducing artifacts and improving perceptual similarity without significant computational overhead.
Contribution
The paper proposes a novel GIA module that effectively incorporates global information into U-Nets for low-light imaging, demonstrating improved performance over existing methods.
Findings
Outperforms state-of-the-art methods on real-world low-light datasets
Enhances perceptual similarity metrics in low-light image reconstruction
Effective global information integration with negligible additional cost
Abstract
It is extremely challenging to acquire perceptually plausible images under low-light conditions due to low SNR. Most recently, U-Nets have shown promising results for low-light imaging. However, vanilla U-Nets generate images with artifacts such as color inconsistency due to the lack of global color information. In this paper, we propose a global information aware (GIA) module, which is capable of extracting and integrating the global information into the network to improve the performance of low-light imaging. The GIA module can be inserted into a vanilla U-Net with negligible extra learnable parameters or computational cost. Moreover, a GIA-Net is constructed, trained and evaluated on a large scale real-world low-light imaging dataset. Experimental results show that the proposed GIA-Net outperforms the state-of-the-art methods in terms of four metrics, including deep metrics that…
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.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsConcatenated Skip Connection · Max Pooling · *Communicated@Fast*How Do I Communicate to Expedia? · Convolution · U-Net
