AFF‐Dehazing: Attention‐based feature fusion network for low‐light image Dehazing

Abstract

Images captured in haze conditions, especially at nighttime with low light, often suffer from degraded visibility, contrasts, and vividness, which makes it difficult to carry out the following vision tasks. In this article, we propose an attention-based feature fusion network (AFF-Dehazing) for low-light image dehazing. Our method decomposes the low-light image dehazing into two task-independent streams containing four modules: image dehazing module, low-light feature extractor module, feature fusion module, and image restoration module. The basic block of these modules is the proposed attention-based residual dense block. Since the dual-branch are used, AFF-Dehazing can avoid learning the mixed degradation all-in-one and enhance the details of low-light haze images. Extensive experiments show that our method surpasses previous state-of-the-art image dehazing methods and low-light enhancement methods by a very large margin both quantitatively and qualitatively. K E Y W O R D S attention mechanism, image dehazing, low-light enhancement INTRODUCTIONHaze is common atmospheric phenomenon and often plagues the qualities of the images acquired by the cameras. While, at night with low light, the images further face severe degradations, including low visibility and intensity blurs. Recently, many efforts have been made to solve the problems of image dehazing and low-light image enhancement. However, existing methods dealt with the problems of image dehazing and low-light enhancement separately. These methods can achieve relatively good performance on corrupted images when removing a certain target type of distortion (i.e., haze or low-light), but they are not effective in removing both types of distortions.

Review and evaluation of recent advancements in image dehazing techniques for vision improvement and visualization

“…Zhou et al 84 . proposed an attention-based feature fusion network (AFF-Net) for low-light image dehazing.…”

“…Non-Learning based Contrast Maximizing [62] Dark Channel Prior [36] Dehaze net [63] AdaFM-Net [12] MPAB [91] QCNN-H [72] Deep-CNN [87] LIDN [85] RRANet [13] NLNet [92] DLA [94] SCR-Net [93] AFF-Net [84] LMFAN [89] LSA-Module [88] CBAM [90] Proximal DehazeNet [105] NIN Dehazenet [111] MSCNN [64] AOD net [67] Improved Dark Channel [61] DCP Using Histogram Specification [19] DCP Using Guided Filter [22,25,26,29] ICA [39] Dark Channel Anisotropic diffusion [38] Color Attenuation Prior [60] Attention Mechanism based…”

“…where β and μ are the standard deviations and mean of the batch size, α and δ are denoted as affine parameters. Zhou et al 84 proposed an attention-based feature fusion network (AFF-Net) for low-light image dehazing. The AFF-Net comprises a feature extraction module, an attention-based residual dense block (ABRDB), and a reconstruction module.…”

An encoder‐decoder based CNN architecture using end to end dehaze and detection network for proper image visualization and detection

“…CNNs have attained great success in several image processing applications like image segmentation, image enhancement, object identification, and image dehazing. [14][15][16][17] Zhou et al 18 proposed CNN-based framework for atmospheric light estimation from the input hazy images. End-to-end framework-based CNN was adopted by Cai et al, 19 and the main drawback is that the transmission map of this method is inaccurate.…”