You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network

نویسندگان

چکیده

In this paper, we study two challenging and less-touched problems in single image dehazing, namely, how to make deep learning achieve dehazing without training on the ground-truth clean (unsupervised) an collection (untrained). An unsupervised model will avoid intensive labor of collecting hazy-clean pairs, untrained is a “real” approach which could remove haze based observed hazy only no extra images are used. Motivated by layer disentanglement, propose novel method, called you look yourself (YOLY) be one first neural networks for dehazing. brief, YOLY employs three joint subnetworks separate into several latent layers, i.e., scene radiance layer, transmission map atmospheric light layer. After that, layers further composed self-supervised manner. Thanks characteristics YOLY, our method bypasses conventional paradigm models pairs or large scale dataset, thus avoids labor-intensive data domain shift issue. Besides, also provides effective learning-based transfer solution thanks its disentanglement mechanism. Extensive experiments show promising performance compared with 14 methods six databases. The code accessed at www.pengxi.me.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Cascaded Convolutional Neural Network for Single Image Dehazing

Images captured under outdoor scenes usually suffer from low contrast and limited visibility due to suspended atmospheric particles, which directly affects the quality of photos. Despite numerous image dehazing methods have been proposed, effective hazy image restoration remains a challenging problem. Existing learning-based methods usually predict the medium transmission by Convolutional Neura...

متن کامل

Gated Fusion Network for Single Image Dehazing

In this paper, we propose an efficient algorithm to directly restore a clear image from a hazy input. The proposed algorithm hinges on an end-to-end trainable neural network that consists of an encoder and a decoder. The encoder is exploited to capture the context of the derived input images, while the decoder is employed to estimate the contribution of each input to the final dehazed result us...

متن کامل

Single Image Dehazing via Multi-scale Convolutional Neural Networks

The performance of existing image dehazing methods is limited by hand-designed features, such as the dark channel, color disparity and maximum contrast, with complex fusion schemes. In this paper, we propose a multi-scale deep neural network for single-image dehazing by learning the mapping between hazy images and their corresponding transmission maps. The proposed algorithm consists of a coars...

متن کامل

Improved Single Image Dehazing Using Guided Filter

Single image dehazing is challenging because it is massively ill-posed. Haze removal based on dark channel prior is effective, but refining the transmission map with closed-form matting is computationally expensive. Recent work discovered that using guided filter to refine the transmission map is feasible. In this paper, we elaborate single image dehazing by combining dark channel prior and gui...

متن کامل

Single Image Dehazing Algorithm Based on Dark Channel Prior and Inverse Image

The sky regions of foggy image processed by all the existing conventional dehazing methods are degraded by color distortion and severe noise. This paper proposes an improved algorithm which combines dark channel prior and inverse image. We first invert the foggy image, and then estimate the transmission of the inverse image. At last, compared with the non-inversed transmission, the larger value...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: International Journal of Computer Vision

سال: 2021

ISSN: ['0920-5691', '1573-1405']

DOI: https://doi.org/10.1007/s11263-021-01431-5