Dual-Stage Global and Local Feature Framework for Image Dehazing
By: Anas M. Ali, Anis Koubaa, Bilel Benjdira
Potential Business Impact:
Clears fog from big, detailed pictures.
Addressing the challenge of removing atmospheric fog or haze from digital images, known as image dehazing, has recently gained significant traction in the computer vision community. Although contemporary dehazing models have demonstrated promising performance, few have thoroughly investigated high-resolution imagery. In such scenarios, practitioners often resort to downsampling the input image or processing it in smaller patches, which leads to a notable performance degradation. This drop is primarily linked to the difficulty of effectively combining global contextual information with localized, fine-grained details as the spatial resolution grows. In this chapter, we propose a novel framework, termed the Streamlined Global and Local Features Combinator (SGLC), to bridge this gap and enable robust dehazing for high-resolution inputs. Our approach is composed of two principal components: the Global Features Generator (GFG) and the Local Features Enhancer (LFE). The GFG produces an initial dehazed output by focusing on broad contextual understanding of the scene. Subsequently, the LFE refines this preliminary output by enhancing localized details and pixel-level features, thereby capturing the interplay between global appearance and local structure. To evaluate the effectiveness of SGLC, we integrated it with the Uformer architecture, a state-of-the-art dehazing model. Experimental results on high-resolution datasets reveal a considerable improvement in peak signal-to-noise ratio (PSNR) when employing SGLC, indicating its potency in addressing haze in large-scale imagery. Moreover, the SGLC design is model-agnostic, allowing any dehazing network to be augmented with the proposed global-and-local feature fusion mechanism. Through this strategy, practitioners can harness both scene-level cues and granular details, significantly improving visual fidelity in high-resolution environments.
Similar Papers
GUSL-Dehaze: A Green U-Shaped Learning Approach to Image Dehazing
Image and Video Processing
Clears foggy pictures without slow computer brains.
Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images
CV and Pattern Recognition
Clears foggy pictures without losing detail.
Feature Fusion Attention Network with CycleGAN for Image Dehazing, De-Snowing and De-Raining
CV and Pattern Recognition
Clears foggy pictures, showing details hidden by haze.