《Multi-Scale Residual Learning-using a Cycle Spinning CNN for Single Image De-Raining》

de-raining跟超分一样，应该都属于low-level vision的问题。之前的博客《论文阅读笔记之——《Moiré Photo Restoration Using Multiresolution Convolutional Neural Networks》》介绍的去摩尔纹应该也算是同类型的问题。

一开始我认为，这类型的任务跟去噪任务非常像。

Single image de-raining is an extremely challenging problem since the rainy image may contain rain streaks which may vary in size, direction and density.

作者提到，之前的方法的一个缺陷是One of the major limitations of these approaches is that they do not consider the location information of rain drops in the image.（为啥需要考虑雨滴的位置呢？）the proposed Uncertainty guided Multi-scale Residual Learning (UMRL) network attempts to address this issue by learning the rain content at different scales and using them to estimate the final derained output.

作者在introduction认为their algorithm tends to introduce some artifacts in the final de-rained images.那么所谓的位置信息，其实是语义信息，这样的话，其出发点跟SFTGAN是相类似的。比如在人脸、花的地方，会引入artifacts

we make use of the observation that rain streak density and direction does not change drastically with different scales. Rather than relying on the rain density information (i.e. heavy, medium or light) present in the rainy image, we develop a method in which the rain streak （条纹） location information is taken in to consideration in a multiscale fashion to improve the de-raining performance.

也是采用Unet architecture with skip connections的结构作为base model

cycle spinning framework was originally proposed to remove the artifacts introduced by orthogonal wavelets in image de-noising. Similar to wavelets, deep learning-based methods also introduce some artifacts near the edges of the de-rained images。Cycle spinning has been successfully applied to reduce the artifacts introduced near the edges in many applications including image de-blurring and de-noising.

Unlike many deep learning-based methods that directly estimate the de-rained image from the noisy observation, we take a different approach in which we first estimate the rain streak component ˆr (i.e. residual map) and then use it to estimate the de-rained image as ˆx = y − ˆr.

the residual map and its corresponding confidence map were able to capture the regions where there is high probability of incorrect estimates.

《Multi-Scale Residual Learning-using a Cycle Spinning CNN for Single Image De-Raining》相关推荐

ICCV 2017 CREST：《CREST: Convolutional Residual Learning for Visual Tracking》论文笔记
目录动机主要贡献整体框架详细介绍重构DCF 剩余学习 Spatial层 Temporal层跟踪过程实验结果动机本文基于DCF进行改进,摘要中提到,基于DCF的跟踪器无法受益于端到端的 ...
论文阅读笔记《Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval from a Single Image》
核心思想本文提出一种通过图块匹配寻找图像和CAD模型之间的对应关系,并进一步实现位姿估计的算法.与许多从单目图像中实现目标物体三维识别并估计位姿的方法类似,本文也是通过从CAD模型库中检索最相似 ...
深度学习论文阅读图像分类篇（五）：ResNet《Deep Residual Learning for Image Recognition》
深度学习论文阅读图像分类篇(五):ResNet<Deep Residual Learning for Image Recognition> Abstract 摘要 1. Introduct ...
《MA‑CRNN: a multi‑scale attention CRNN for Chinese text line recognition in natural scenes》论文阅读
参考博文: CRNN的一个变种,可以读一读,看看相对于CRNN来说有什么变化?以及为什么? 文章目录 make decision step1:读摘要 step2:读Introduction step3 ...
#论文《Deep Residual Learning for Image Recognition》
2015年的paper,微软何凯明等. 解决的问题: 梯度消失/爆炸问题: 之前的解决方案:This problem, however, has been largely addressed by n ...
重读经典：《Deep Residual Learning for Image Recognition》
ResNet论文逐段精读[论文精读] 这是李沐博士论文精读的第二篇论文,这次精读的论文是ResNet.ResNet 是 CVPR2016 的最佳论文,目前谷歌学术显示其被引用数已经达到了90000+. ...
读文献——《Deep Residual Learning for Image Recognition》
1.Abstract We present a residual learning framework to ease the training of networks that are substa ...
【HRNet】《Deep High-Resolution Representation Learning for Human Pose Estimation》
CVPR-2019 代码:https://github.com/leoxiaobin/deep-high-resolution-net.pytorch 文章目录 1 Background and Mo ...
Paper之BigGAN：《Large Scale Gan Training For High Fidelity Natural Image Synthesis》翻译与解读
Paper之BigGAN:<Large Scale Gan Training For High Fidelity Natural Image Synthesis>翻译与解读目录效果 1 ...

《Multi-Scale Residual Learning-using a Cycle Spinning CNN for Single Image De-Raining》

《Multi-Scale Residual Learning-using a Cycle Spinning CNN for Single Image De-Raining》相关推荐

最新文章

热门文章