VALSE

VALSE 首页 活动通知 查看内容

VALSE 论文速览 第173期:基于通道选择归一化的通用图像光照调整方法 ...

2024-5-21 13:35| 发布者: 程一-计算所| 查看: 883| 评论: 0

摘要: 为了使得视觉与学习领域相关从业者快速及时地了解领域的最新发展动态和前沿技术进展,VALSE最新推出了《论文速览》栏目,将在每周发布一至两篇顶会顶刊论文的录制视频,对单个前沿工作进行细致讲解。本期VALSE论文速 ...

为了使得视觉与学习领域相关从业者快速及时地了解领域的最新发展动态和前沿技术进展,VALSE最新推出了《论文速览》栏目,将在每周发布一至两篇顶会顶刊论文的录制视频,对单个前沿工作进行细致讲解。本期VALSE论文速览选取了来自中国科学技术大学的图像增强泛化 (Generalized Image enhancement)的工作。该工作由论文一作姚明德同学录制。


论文题目:

Generalized Lightness Adaptation with Channel Selective Normalization

作者列表:

Mingde Yao (中国科学技术大学)、Jie Huang (中国科学技术大学)、Xin Jin (东方理工大学)、Ruikang Xu (中国科学技术大学)、Shenglong Zhou (中国科学技术大学)、Man Zhou (中国科学技术大学)、Zhiwei Xiong (中国科学技术大学)


B站观看网址:

https://www.bilibili.com/video/BV1NZ421b752/



论文摘要:

Lightness adaptation is vital to the success of image processing to avoid unexpected visual deterioration, which covers multiple aspects, e.g., low-light image enhancement, image retouching, and inverse tone mapping. Existing methods typically work well on their trained lightness conditions but perform poorly in unknown ones due to their limited generalization ability. To address this limitation, we propose a novel generalized lightness adaptation algorithm that extends conventional normalization techniques through a channel filtering design, dubbed Channel Selective Normalization (CSNorm). The proposed CSNorm purposely normalizes the statistics of lightness-relevant channels and keeps other channels unchanged, so as to improve feature generalization and discrimination. To optimize CSNorm, we propose an alternating training strategy that effectively identifies lightness-relevant channels. The model equipped with our CSNorm only needs to be trained on one lightness condition and can be well generalized to unknown lightness conditions. Experimental results on multiple benchmark datasets demonstrate the effectiveness of CSNorm in enhancing the generalization ability for the existing lightness adaptation methods.


参考文献:

[1] Mingde Yao, Jie Huang, Xin Jin, Ruikang Xu, Shenglong Zhou, Man Zhou, Zhiwei Xiong, “Generalized Lightness Adaptation with Channel Selective Normalization.” In Proceeding of IEEE International Conference on Computer Vision (ICCV), 2023.


论文链接:

[https://arxiv.org/pdf/2308.13783.pdf]

 

代码链接:

[https://github.com/mdyao/CSNorm]

 

视频讲者简介:

姚明德,中国科学技术大学博士生,师从熊志伟教授,主要研究方向为计算成像、底层视觉。在CVPR、ICCV、NeurIPS、TMM等会议和期刊发表多篇论文,担任多个学术会议和期刊的审稿人。


个人主页:

https://mdyao.github.io/



特别鸣谢本次论文速览主要组织者:

月度轮值AC:陆昊 (华中科技大学)


活动参与方式

1、VALSE每周举行的Webinar活动依托B站直播平台进行,欢迎在B站搜索VALSE_Webinar关注我们!

直播地址:

https://live.bilibili.com/22300737;

历史视频观看地址:

https://space.bilibili.com/562085182/ 


2、VALSE Webinar活动通常每周三晚上20:00进行,但偶尔会因为讲者时区问题略有调整,为方便您参加活动,请关注VALSE微信公众号:valse_wechat 或加入VALSE QQ T群,群号:863867505);


*注:申请加入VALSE QQ群时需验证姓名、单位和身份缺一不可。入群后,请实名,姓名身份单位。身份:学校及科研单位人员T;企业研发I;博士D;硕士M。


3、VALSE微信公众号一般会在每周四发布下一周Webinar报告的通知。


4您也可以通过访问VALSE主页:http://valser.org/ 直接查看Webinar活动信息。Webinar报告的PPT(经讲者允许后),会在VALSE官网每期报告通知的最下方更新。

小黑屋|手机版|Archiver|Vision And Learning SEminar

GMT+8, 2024-11-23 09:18 , Processed in 0.012479 second(s), 14 queries .

Powered by Discuz! X3.4

Copyright © 2001-2020, Tencent Cloud.

返回顶部