RGB-D salient object detection via deep fusion of semantics and details,Computer Animation and Virtual Worlds

当前位置： X-MOL 学术 › Comput. Animat. Virtual Worlds › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

RGB-D salient object detection via deep fusion of semantics and details
Computer Animation and Virtual Worlds ( IF 0.9 ) Pub Date : 2020-07-01 , DOI: 10.1002/cav.1954
Shimin Zhao ₁ , Miaomiao Chen ₁ , Pengjie Wang ₁ , Ying Cao ₂ , Pingping Zhang ₃ , Xin Yang ₃

Affiliation

In this paper, we address RGB‐D salient object detection task by jointly leveraging semantics and contour details of salient objects. We propose a novel semantics‐and‐details complementary fusion network to adaptively integrate cross‐model and multilevel features. Specifically, we employ two kinds of fusion modules in our model, which are designed for fusing high‐level semantic features and integrating contour detail features of the scene components, respectively. The semantics fusion module aggregates high‐level interdependent semantic relationships by a nonlinear weighted summation of small and medium receptive fields. Meanwhile, the details module integrates multi‐level contour detail features to leverage expressive details of salient objects. We achieve new state‐of‐the‐art salient object detection results on seven RGB‐D datasets, that is, STERE, NJU2000, LFSD, NLPR, SSD, DES, and SIP2019 dataset. Experimental results demonstrate that our method outperforms eleven state‐of‐the‐art salient object detection methods.

中文翻译：

通过语义和细节的深度融合进行 RGB-D 显着目标检测

在本文中，我们通过联合利用显着对象的语义和轮廓细节来解决 RGB-D 显着对象检测任务。我们提出了一种新颖的语义和细节互补融合网络，以自适应地集成跨模型和多级特征。具体来说，我们在模型中采用了两种融合模块，它们分别用于融合高级语义特征和集成场景组件的轮廓细节特征。语义融合模块通过中小感受野的非线性加权求和来聚合高层相互依赖的语义关系。同时，细节模块集成了多级轮廓细节特征，以利用显着对象的表现细节。我们在七个 RGB-D 数据集上实现了新的最先进的显着对象检测结果，即，STERE、NJU2000、LFSD、NLPR、SSD、DES 和 SIP2019 数据集。实验结果表明，我们的方法优于十一种最先进的显着物体检测方法。

更新日期：2020-07-01

点击分享查看原文

点击收藏

阅读更多本刊最新论文本刊介绍/投稿指南11