RGB-D salient object detection: A survey (2020-08-01T00:00:00.000000Z)

TL;DR

This paper provides a comprehensive survey of RGB-D based salient object detection models from various perspectives, and review related benchmark datasets in detail, and investigates the ability of existing models to detect salient objects.

Abstract

Salient object detection, which simulates human visual perception in locating the most significant object(s) in a scene, has been widely applied to various computer vision tasks. Now, the advent of depth sensors means that depth maps can easily be captured; this additional spatial information can boost the performance of salient object detection. Although various RGB-D based salient object detection models with promising performance have been proposed over the past several years, an in-depth understanding of these models and the challenges in this field remains lacking. In this paper, we provide a comprehensive survey of RGB-D based salient object detection models from various perspectives, and review related benchmark datasets in detail. Further, as light fields can also provide depth maps, we review salient object detection models and popular benchmark datasets from this domain too. Moreover, to investigate the ability of existing models to detect salient objects, we have carried out a comprehensive attribute-based evaluation of several representative RGB-D based salient object detection models. Finally, we discuss several challenges and open directions of RGB-D based salient object detection for future research. All collected models, benchmark datasets, datasets constructed for attribute-based evaluation, and related code are publicly available at https://github.com/taozh2017/RGBD-SODsurvey.

Authors

Jianbing Shen

16 papers

Ling Shao

32 papers

Ming-Ming Cheng

30 papers

TL;DR

Abstract

Authors

References210 items

See More: Learn about Viking women, doughnuts in the brain, nuclear weapons, and more in the October issue of Scientific American.

Global and Local-Contrast Guides Content-Aware Fusion for RGB-D Saliency Prediction

Automatic COVID-19 Lung Infection Segmentation from CT Images

Discriminative Cross-Modal Transfer Learning and Densely Cross-Level Feedback Fusion for RGB-D Salient Object Detection

Feature Reintegration over Differential Treatment: A Top-down and Adaptive Fusion Network for RGB-D Salient Object Detection

Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection

RGBD Salient Object Detection via Disentangled Cross-Modal Fusion

Depth-Quality-Aware Salient Object Detection

Data-Level Recombination and Lightweight Fusion Scheme for RGB-D Salient Object Detection

Cascade Graph Neural Networks for RGB-D Salient Object Detection

Knowing Depth Quality In Advance: A Depth Quality Assessment Method For RGB-D Salient Object Detection

CoCNN: RGB-D deep fusion for stereoscopic salient object detection

Going From RGB to RGBD Saliency: A Depth-Guided Transformation Model

Accurate RGB-D Salient Object Detection via Collaborative Learning

A Single Stream Network for Robust and Real-time RGB-D Salient Object Detection

RGB-D Salient Object Detection with Cross-Modality Modulation and Selection

Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detection

Multi-level Cross-modal Interaction Network for RGB-D Salient Object Detection

Cross-Modal Weighting Network for RGB-D Salient Object Detection

RGBT Salient Object Detection: A Large-Scale Dataset and Benchmark

Re-Thinking Co-Salient Object Detection

BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network

Synergistic saliency and depth prediction for RGB-D saliency detection

Salient object detection for RGB-D images by generative adversarial network

PraNet: Parallel Reverse Attention Network for Polyp Segmentation

Learning Selective Self-Mutual Attention for RGB-D Saliency Detection

A2dele: Adaptive and Attentive Depth Distiller for Efficient RGB-D Salient Object Detection

Select, Supplement and Focus for RGB-D Saliency Detection

Camouflaged Object Detection

SDC-Depth: Semantic Divide-and-Conquer Network for Monocular Depth Estimation

Geometric Structure Based and Regularized Depth Estimation From 360 Indoor Imagery

Is Depth Really Necessary for Salient Object Detection?

GFNet: Gate Fusion Network With Res2Net for Detecting Salient Objects in RGB-D Images

Multi-interactive Encoder-decoder Network for RGBT Salient Object Detection

Bilateral Attention Network for RGB-D Salient Object Detection

LFNet: Light Field Fusion Network for Salient Object Detection

Region-based depth feature descriptor for saliency detection on light field

Triple-Complementary Network for RGB-D Salient Object Detection

Inf-Net: Automatic COVID-19 Lung Infection Segmentation From CT Images

JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection

JCS: An Explainable COVID-19 Diagnosis System by Joint Classification and Segmentation

UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders

Exploit and Replace: An Asymmetrical Two-Stream Architecture for Versatile Light Field Saliency Detection

A cross-modal adaptive gated fusion generative adversarial network for RGB-D salient object detection

Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning

DPANet: Depth Potentiality-Aware Gated Attention Network for RGB-D Salient Object Detection

ICNet: Information Conversion Network for RGB-D Based Salient Object Detection

Attention-guided RGBD saliency detection using appearance information

ASIF-Net: Attention Steered Interweave Fusion Network for RGB-D Salient Object Detection

Hi-Net: Hybrid-Fusion Network for Multi-Modal MR Image Synthesis

Multi-Modal Weights Sharing and Hierarchical Feature Fusion for RGBD Salient Object Detection

Improved Saliency Detection in RGB-D Images Using Two-Phase Depth Estimation and Selective Deep Fusion

Multi-modal latent space inducing ensemble SVM classifier for early dementia diagnosis with neuroimaging data

cmSalGAN: RGB-D Salient Object Detection With Cross-View Generative Adversarial Networks

RGB-T Salient Object Detection via Fusing Multi-Level CNN Features

Language-aware weak supervision for salient object detection

SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans

RGB-T Saliency Detection via Robust Graph Learning and Collaborative Manifold Ranking

Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection

Deep Learning for Light Field Saliency Detection

Salient object detection for RGB-D image by single stream recurrent convolution neural network

Co-Saliency Detection for RGBD Images Based on Effective Propagation Mechanism

CNN-based RGB-D Salient Object Detection: Learn, Select and Fuse

Joint Learning of Saliency Detection and Weakly Supervised Semantic Segmentation

Two-Stream Refinement Network for RGB-D Saliency Detection

EGNet: Edge Guidance Network for Salient Object Detection

Semi-Supervised Video Salient Object Detection Using Pseudo-Labels

Deep Light-field-driven Saliency Detection from a Single View

Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks

Light Field Saliency Detection With Deep Convolutional Networks

Shifting More Attention to Video Salient Object Detection

Multi-Level Context Ultra-Aggregation for Stereo Matching

Deep Modular Co-Attention Networks for Visual Question Answering

See More, Know More: Unsupervised Video Object Segmentation With Co-Attention Siamese Networks

Salient Object Detection With Pyramid Attention and Salient Edges

Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection