paper-with-me

홈 › Papers

Efficient Re-parameterization Residual Attention Network For Nonhomogeneous Image Dehazing

2021-09-12 · Tian Ye, ErKang Chen, XinRui Huang, Peng Chen

This paper proposes an end-to-end Efficient Re-parameterizationResidual Attention Network(ERRA-Net) to directly restore the nonhomogeneous hazy image. The contribution of this paper mainly has the following three aspects: 1) A novel Multi-branch Attention (MA) block. The spatial attention mechanism better reconstructs high-frequency features, and the channel attention mechanism treats the features of different channels differently. Multi-branch structure dramatically improves the representation ability of the model and can be changed into a single path structure after re-parameterization to speed up the process of inference. Local Residual Connection allows the low-frequency information in the nonhomogeneous area to pass through the block without processing so that the block can focus on detailed features. 2) A lightweight network structure. We use cascaded MA blocks to extract high-frequency features step by step, and the Multi-layer attention fusion tail combines the shallow and deep features of the model to get the residual of the clean image finally. 3)We propose two novel loss functions to help reconstruct the hazy image ColorAttenuation loss and Laplace Pyramid loss. ERRA-Net has an impressive speed, processing 1200x1600 HD quality images with an average runtime of 166.11 fps. Extensive evaluations demonstrate that ERSANet performs favorably against the SOTA approaches on the real-world hazy images.

📄 PDF Abstract BibTeX arXiv:2109.05479

Code (1)

Owen718/ERA-Net 공식 구현

Tasks

Image DehazingNonhomogeneous Image Dehazing

Methods 이 논문이 사용한 방법론

Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

NTIRE 2020 Challenge on NonHomogeneous Dehazing

2020-05-07 · Codruta O. Ancuti, Cosmin Ancuti, Florin-Alexandru Vasluianu, Radu Timofte 외

This paper reviews the NTIRE 2020 Challenge on NonHomogeneous Dehazing of images (restoration of rich details in hazy image). We focus on the proposed solutions and their results evaluated on NH-Haze, a novel dataset con…

Image Dehazing

Fast Deep Multi-patch Hierarchical Network for Nonhomogeneous Image Dehazing

2020-05-12 · IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2020 6 · Sourya Dipta Das, Saikat Dutta

Recently, CNN based end-to-end deep learning methods achieve superiority in Image Dehazing but they tend to fail drastically in Non-homogeneous dehazing. Apart from that, existing popular Multi-scale approaches are runti…

Image DehazingNonhomogeneous Image Dehazing

SelfPromer: Self-Prompt Dehazing Transformers with Depth-Consistency

2023-03-13 · Cong Wang, Jinshan Pan, WanYu Lin, Jiangxin Dong 외

This work presents an effective depth-consistency self-prompt Transformer for image dehazing. It is motivated by an observation that the estimated depths of an image with haze residuals and its clear counterpart vary. En…

Image DehazingImage Generation

Implicit Euler ODE Networks for Single-Image Dehazing

2020-07-13 · Jiawei Shen, Zhuoyan Li, Lei Yu, Gui-Song Xia 외

Deep convolutional neural networks (CNN) have been applied for image dehazing tasks, where the residual network (ResNet) is often adopted as the basic component to avoid the vanishing gradient problem. Recently, many wor…

Image DehazingSingle Image Dehazing

Distilling Image Dehazing With Heterogeneous Task Imitation

2020-06-01 · CVPR 2020 6 · Ming Hong, Yuan Xie, Cuihua Li, Yanyun Qu

State-of-the-art deep dehazing models are often difficult in training. Knowledge distillation paves a way to train a student network assisted by a teacher network. However, most knowledge distill methods are used for ima…

image-classificationImage ClassificationImage DehazingImage Reconstruction+5