arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2211.14751cs.CV
收藏

从单张图像估计反射层:融合反射引导与阴影/高光感知学习

Estimating Reflectance Layer from A Single Image: Integrating Reflectance Guidance and Shadow/Specular Aware Learning

National University of Singapore(新加坡国立大学);ByteDance(字节跳动);Peng Cheng Laboratory(鹏城实验室);Yale-NUS College(耶鲁-新加坡国大学院)

Yeying Jin, Ruoteng Li, Wenhan Yang, Robby T. Tan

AI总结:

本文提出一种两阶段学习方法,先通过反射引导获得无阴影和高光的初始反射层,再利用S-Aware网络以注意力机制细化估计,在单图反射层估计中优于现有方法。

摘要:

从单张图像估计反射层是一项具有挑战性的任务。当输入图像包含阴影或镜面高光时,这一任务变得更加困难,因为这些因素往往会导致反射层估计不准确。因此,我们提出了一种两阶段学习方法,包括反射引导和一个阴影/高光感知(S-Aware)网络来解决该问题。在第一阶段,通过由基于先验的无阴影和无高光图像引导的新型损失函数约束,获得一个不含阴影和镜面高光的初始反射层。为了在第二阶段细化中进一步强制反射层独立于阴影和镜面高光,我们引入了一个S-Aware网络,用于区分反射图像与输入图像。我们的网络采用一个分类器对阴影/无阴影、高光/无高光类别进行分类,使激活特征能够作为关注阴影/高光区域的注意力图。我们的定量和定性评估表明,在估计不含阴影和镜面高光的反射层方面,我们的方法优于当前最先进的方法。代码位于:\url{https://github.com/jinyeying/S-Aware-network}。

英文摘要:

Estimating the reflectance layer from a single image is a challenging task. It becomes more challenging when the input image contains shadows or specular highlights, which often render an inaccurate estimate of the reflectance layer. Therefore, we propose a two-stage learning method, including reflectance guidance and a Shadow/Specular-Aware (S-Aware) network to tackle the problem. In the first stage, an initial reflectance layer free from shadows and specularities is obtained with the constraint of novel losses that are guided by prior-based shadow-free and specular-free images. To further enforce the reflectance layer to be independent of shadows and specularities in the second-stage refinement, we introduce an S-Aware network that distinguishes the reflectance image from the input image. Our network employs a classifier to categorize shadow/shadow-free, specular/specular-free classes, enabling the activation features to function as attention maps that focus on shadow/specular regions. Our quantitative and qualitative evaluations show that our method outperforms the state-of-the-art methods in the reflectance layer estimation that is free from shadows and specularities. Code is at: \url{https://github.com/jinyeying/S-Aware-network}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑