RGBD Salient Object Detection via Deep Fusion

By Liangqiong Qu, Shengfeng He, Jiawei Zhang, Jiandong Tian, Yandong Tang, Qingxiong Yang. IEEE Transactions on Image Processing, 2016

370 citations recorded by the source corpus.

Numerous efforts have been made to design various low-level saliency cues for RGBD saliency detection, such as color and depth contrast features as well as background and color compactness priors. However, how these low-level saliency cues interact with each other and how they can be effectively incorporated to generate a master saliency map remain challenging problems. In this paper, we design a new convolutional neural network (CNN) to automatically learn the interaction mechanism for RGBD salient object detection. In contrast to existing works, in which raw image pixels are fed directly to the CNN, the proposed method takes advantage of the knowledge obtained in traditional saliency detection by adopting various flexible and interpretable saliency feature vectors as inputs. This guides the CNN to learn a combination of existing features to predict saliency more effectively, which presents a less complex problem than operating on the pixels directly. We then integrate a superpixel-based Laplacian propagation framework with the trained CNN to extract a spatially consistent saliency map by exploiting the intrinsic structure of the input image. Extensive quantitative and qualitative experimental evaluations on three data sets demonstrate that the proposed method consistently outperforms the state-of-the-art methods.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e0ca5c9dbdf515778affc7636ae2268b239b57b9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Suppress and Balance: A Simple Gated Network for Salient Object Detection (2020, methodology): “datasets, including the DES [9], DCMC [11], CDCP [75], DF [38], CTMF [18], PCA [3], MMCI [5], TANet [4], CPFP [71] and DMRA [36].”
UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders (2020, methodology): “[41] [36] [8] [44] [66] [28] [20] [10] [51] [22] [43] [54] [24] [7] [5] [6] [64] [61] Ours”
JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection (2020, methodology): “The ﬁrst model utilizing convolutional neural networks (CNNs) for RGB-D SOD [49], which adopts a shallow CNN as the saliency map integration model, was described in 2017.”
Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks (2019, background): “BED [76] and DF [44] are two pioneering works for this, which introduced deep learning technology into the RGB-D based SOD task.”
BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network (2020, methodology): “trengths for the segmented regions. Ciptadi et al. [63] used surface normals and color contrast to compute saliency. However, the local contrast methods are easily disturbed by high-frequency content [64], since they mainly rely on the boundaries of salient objects. Therefore, some algorithms, such ”
Progressively Complementarity-Aware Fusion Network for RGB-D Salient Object Detection (2018, methodology): “We compare our method with LBE [37], MDSF [38], EGP [36], NLPR [39], ACSD [34], SRDS [35] and two recent RGB-D saliency detection networks DF [18] and CTMF [19].”
Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection (2019, methodology): “We compare our model with 9 RGBD based salient object detection models including LHM [42], GP [45], LBE [20], SE [23], CTMF [25], DF [44], MDSF [49], CDCP [57], and PCF [4].”
Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection (2019, methodology): “We compare our method with 16 state-of-the-art ones, including 5 latest CNNs-based RGB-D methods: PCA [3], PDNet [48], MMCI [4], CTMF [18], DF [35]; 5 traditional RGB-D methods: MB [49], CDCP [50], NLPR [32], DES [8], DCMC [9]; 6 top ranking CNNs-based RGB methods: PiCANet [30], PAGRN [47], R(3)Net ”
Review of Visual Saliency Detection With Comprehensive Information (2018, methodology): “For evaluating the running time, we tested the typical saliency detection methods, including single image saliency (DCLC [28] and SMD [29]), RGBD saliency (DF [60]), cosaliency (CCS [80]), and RGBD co-saliency (MCLP [91]), on a Quad Core 3.”