RGB-D Salient Object Detection: A Survey

Abstract

Salient object detection (SOD), which simulates the human visual perception system to locate the most attractive object(s) in a scene, has been widely applied to various computer vision tasks. Now, with the advent of depth sensors, depth maps with affluent spatial information that can be beneficial in boosting the performance of SOD, can easily be captured. Although various RGB-D based SOD models with promising performance have been proposed over the past several years, an in-depth understanding of these models and challenges in this topic remains lacking. In this paper, we provide a comprehensive survey of RGB-D based SOD models from various perspectives, and review related benchmark datasets in detail. Further, considering that the light field can also provide depth maps, we review SOD models and popular benchmark datasets from this domain as well. Moreover, to investigate the SOD ability of existing models, we carry out a comprehensive evaluation, as well as attribute-based evaluation of several representative RGB-D based SOD models. Finally, we discuss several challenges and open directions of RGB-D based SOD for future research. All collected models, benchmark datasets, source code links, datasets constructed for attribute-based evaluation, and codes for evaluation will be made publicly available at https://github.com/taozh2017/RGBDSODsurvey

arXiv comment25 pages, 14 figures

References in corpus (28)

• Conditional Generative Adversarial Nets
• Salient Object Detection: A Benchmark
• AMC: AutoML for Model Compression and Acceleration on Mobile Devices
• A Survey of Model Compression and Acceleration for Deep Neural Networks
• Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks
• Video Salient Object Detection via Fully Convolutional Networks
• Deep Visual Attention Prediction
• Salient Object Detection: A Survey
• Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network
• Review of Visual Saliency Detection with Comprehensive Information
• JCS: An Explainable COVID-19 Diagnosis System by Joint Classification and Segmentation
• RGBD Salient Object Detection via Deep Fusion
• SalGAN: Visual Saliency Prediction with Generative Adversarial Networks
• Multi-interactive Dual-decoder for RGB-thermal Salient Object Detection
• DPANet: Depth Potentiality-Aware Gated Attention Network for RGB-D Salient Object Detection
• Bilateral Attention Network for RGB-D Salient Object Detection
• Re-thinking Co-Salient Object Detection
• Co-saliency Detection for RGBD Images Based on Multi-constraint Feature Matching and Cross Label Propagation
• Depth Quality Aware Salient Object Detection
• Data-Level Recombination and Lightweight Fusion Scheme for RGB-D Salient Object Detection
• Bridging Saliency Detection to Weakly Supervised Object Detection Based on Self-paced Curriculum Learning
• Joint Learning of Saliency Detection and Weakly Supervised Semantic Segmentation
• A Unified RGB-T Saliency Detection Benchmark: Dataset, Baselines, Analysis and A Novel Approach
• An Integration of Bottom-up and Top-Down Salient Cues on RGB-D Data: Saliency from Objectness vs. Non-Objectness
• CNN-based RGB-D Salient Object Detection: Learn, Select and Fuse
• Knowing Depth Quality In Advance: A Depth Quality Assessment Method For RGB-D Salient Object Detection
• Multi-level Cross-modal Interaction Network for RGB-D Salient Object Detection
• Synergistic saliency and depth prediction for RGB-D saliency detection

Cited by in corpus (18)

• Artificial Intelligence in the Creative Industries: A Review
• CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection
• MobileSal: Extremely Efficient RGB-D Salient Object Detection
• Bifurcated backbone strategy for RGB-D salient object detection
• Re-thinking Co-Salient Object Detection
• Depth Quality Aware Salient Object Detection
• Light Field Salient Object Detection: A Review and Benchmark
• Middle-level Fusion for Lightweight RGB-D Salient Object Detection
• Salient Objects in Clutter
• FakeNews: GAN-based generation of realistic 3D volumetric data -- A systematic review and taxonomy
• Contrast-weighted Dictionary Learning Based Saliency Detection for Remote Sensing Images
• Full-Duplex Strategy for Video Object Segmentation
• Uncertainty Inspired RGB-D Saliency Detection
• UPANets: Learning from the Universal Pixel Attention Networks
• ASOD60K: An Audio-Induced Salient Object Detection Dataset for Panoramic Videos
• Multi-level Cross-modal Interaction Network for RGB-D Salient Object Detection
• A Unified Structure for Efficient RGB and RGB-D Salient Object Detection
• ACFNet: Adaptively-Cooperative Fusion Network for RGB-D Salient Object Detection