期刊
JOURNAL OF SYSTEMS ARCHITECTURE
卷 132, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.sysarc.2022.102736
关键词
Single-image dehazing; Convolutional neural network; Encoder-decoder architecture; Attention; Low-pass filter; High-pass filter
资金
- WNI WxBunka Foundation, Japan
- IIT Roorkee, India [FIG-100874]
In this paper, a novel end-to-end trainable convolutional neural network architecture called ClarifyNet is proposed for single image dehazing. ClarifyNet utilizes low-pass and high-pass filters to extract different types of information and employs a shared-encoder and multi-decoder model structure. By utilizing a weighted loss function, complementary features are extracted and propagated. Experimental results show that ClarifyNet achieves high scores on multiple datasets.
Dehazing refers to removing the haze and restoring the details from hazy images. In this paper, we propose ClarifyNet, a novel, end-to-end trainable, convolutional neural network architecture for single image dehazing. We note that a high-pass filter detects sharp edges, texture, and other fine details in the image, whereas a low-pass filter detects color and contrast information. Based on this observation, our key idea is to train ClarifyNet on ground-truth haze-free images, low-pass filtered images, and high-pass filtered images. Based on this observation, we present a shared-encoder multi-decoder model ClarifyNet which employs interconnected parallelization. While training, ground-truth haze-free images, low-pass filtered images, and high-pass filtered images undergo multi-stage filter fusion and attention. By utilizing a weighted loss function composed of SSIM loss and L1 loss, we extract and propagate complementary features. We comprehensively evaluate ClarifyNet on I-HAZE, O-HAZE, Dense-Haze, NH-HAZE, SOTS-Indoor, SOTS-Outdoor, HSTS, and Middlebury datasets. We use PSNR and SSIM metrics and compare the results with previous works. For most datasets, ClarifyNet provides the highest scores. On using EfficientNet-B6 as the backbone, ClarifyNet has 18 M parameters (model size of similar to 71 MB) and a throughput of 8 frames-per-second while processing images of size 2048 x 1024.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据