RGBD Salient Object Detection: A Benchmark and Algorithms

By Houwen Peng, Bing Li, Weihua Xiong, Weiming Hu, Rongrong Ji. European Conference on Computer Vision, 2014

648 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition, Sensory Systems

View Paper: https://www.semanticscholar.org/paper/fd455bef8dea04acc37f1a4b4be47068bbf58303

How researchers see this paper

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

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

In Sensory Systems

Citations in the corpus

UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders (2020, methodology): “, DES [8], and NLPR [41] datasets; or computing depth from stereo cameras, examples of such datasets are SSB [40] and NJU2K [28].”
Salient Object Detection via Structured Matrix Decomposition (2017, background): “The effectiveness of other complementary cues such as texture [20], depth [52], [53] or surroundedness [54] have also been considered recently.”
Progressively Complementarity-Aware Fusion Network for RGB-D Salient Object Detection (2018, methodology): “Previous RGB-D salient object detection models [31-41] fuse RGB and depth information by three main modes: serializing RGB and depth as undifferentiated 4-channel input (‘input fusion’), combining handcrafted RGB and depth saliency features (‘feature fusion’), or performing unimodal predictions sepa”
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 ”
Self-Supervised Drivable Area and Road Anomaly Segmentation Using RGB-D Data For Robotic Wheelchairs (2019, methodology): “TABLE III: The comparison of road anomaly segmentation results (%) between NLPR [16], FSL (FuseNet trained on the SSLG labels), DSL (Depth-aware CNN trained on the SSLG labels) and RSL (RTFNet trained on the SSLG labels).”
SwinNet: Swin Transformer Drives Edge-Aware RGB-D and RGB-T Salient Object Detection (2022, background): “For the sake of fair comparison, we use the same training dataset as in [78] and [80], which consists of 1,485 images from the NJU2K dataset and 700 images from the NLPR dataset.”
Visual Saliency Transformer (2021, methodology): “For RGB-D SOD, we use nine widely used benchmark datasets: STERE [46] (1,000 image pairs), LFSD [33] (100 image pairs), RGBD135 [9] (135 image pairs), SSD [90] (80 image pairs), NJUD [26] (1,985 image pairs), NLPR [51] (1,000 image pairs), DUTLF-Depth [52] (1,200 image pairs), SIP [15] (929 image pa”
Salient Object Detection: A Benchmark (2015, background): “Although some RGBD datasets exist [118], benchmark datasets for multiple input images (e.”
RGB-D salient object detection: A survey (2020, methodology): “A comprehensive evaluation for 24 representative RGB-D based SOD models, including LHM [51], ACSD [56], DESM [49], GP [50], LBE [57], DCMC [1], SE [2], CDCP [84], CDB [95], DF [52], PCF [92], CTMF [58], CPFP [53], TANet [99], AFNet [102], MMCI [55], DMRA [54], D3Net [3], SSF [4], A2dele [5], S2MA [6”
Saliency Detection on Light Field (2017, positive): “We further choose three recent proposed depthmap-based methods, i.e. SVR [44], LS [30] and RGBD [31], to compare their performances with our model.”
Suppress and Balance: A Simple Gated Network for Salient Object Detection (2020, background): “There are five main RGB-D SOD datasets which are NJUD [23], RGBD135 [9] NLPR [34], SSD [74] and SIP [16].”
JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection (2020, methodology): “The underlying motivation is that, although depth and RGB images come from different modalities, they nevertheless share similar features/cues, such as strong figure-ground contrast [10,43,44], closure of object contours [20,53], and connectivity to image borders [36, 59].”
Review of Visual Saliency Detection With Comprehensive Information (2018, neutral): “[58] calculated the depth saliency through a multi-contextual contrast model, which considers the contrast prior, global distinctiveness, and background cue of depth map.”
Vision-based robotic grasping from object localization, object pose estimation to grasp estimation for parallel grippers: a review (2020, background): “[Peng et al., 2014] proposed a simple fusion strategy which extends RGB-based saliency models by incorporating depth-induced saliency.”
Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection (2019, methodology): “Existing RGBD based SOD methods typically fuse RGB and depth input/features by simple concatenation, either via fusion at an early stage [42, 49], fusion at a late stage [18], or fusion at a middle stage [20], as shown in Fig.”