Jia-Xing Zhao, Yang Cao, Deng-Ping Fan, Ming-Ming Cheng, Xuan-Yi Li, Le Zhang
In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3927-3936. 2019
Publication year: 2019

The large availability of depth sensors provides valu- able complementary information for salient object detec- tion (SOD) in RGBD images. However, due to the inherent difference between RGB and depth information, extracting features from the depth channel using ImageNet pre-trained backbone models and fusing them with RGB features di- rectly are sub-optimal. In this paper, we utilize contrast prior, which used to be a dominant cue in none deep learn- ing based SOD approaches, into CNNs-based architecture to enhance the depth information. The enhanced depth cues are further integrated with RGB features for SOD, using a novel fluid pyramid integration, which can make better use of multi-scale cross-modal features. Comprehensive exper- iments on 5 challenging benchmark datasets demonstrate the superiority of the architecture CPFP over 9 state-of- the-art alternative methods. Project page is available at https://mmcheng.net/rgbdsalpyr/


邮箱地址不会被公开。 必填项已用*标注