Is Depth Really Necessary for Salient Object Detection?

05/30/2020
by   Jiawei Zhao, et al.
15

Salient object detection (SOD) is a crucial and preliminary task for many computer vision applications, which have made progress with deep CNNs. Most of the existing methods mainly rely on the RGB information to distinguish the salient objects, which faces difficulties in some complex scenarios. To solve this, many recent RGBD-based networks are proposed by adopting the depth map as an independent input and fuse the features with RGB information. Taking the advantages of RGB and RGBD methods, we propose a novel depth-aware salient object detection framework, which has following superior designs: 1) It only takes the depth information as training data while only relies on RGB information in the testing phase. 2) It comprehensively optimizes SOD features with multi-level depth-aware regularizations. 3) The depth information also serves as error-weighted map to correct the segmentation process. With these insightful designs combined, we make the first attempt in realizing an unified depth-aware framework with only RGB information as input for inference, which not only surpasses the state-of-the-art performances on five public RGB SOD benchmarks, but also surpasses the RGBD-based methods on five benchmarks by a large margin, while adopting less information and implementation light-weighted. The code and model will be publicly available.

READ FULL TEXT

page 1

page 3

page 5

page 6

page 7

page 8

research
09/08/2021

RGB-D Salient Object Detection with Ubiquitous Target Awareness

Conventional RGB-D salient object detection methods aim to leverage dept...
research
07/16/2022

SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object Detection

RGB-D salient object detection (SOD) has been in the spotlight recently ...
research
05/10/2017

Learning RGB-D Salient Object Detection using background enclosure, depth contrast, and top-down features

Recently, deep Convolutional Neural Networks (CNN) have demonstrated str...
research
12/24/2020

MobileSal: Extremely Efficient RGB-D Salient Object Detection

The high computational cost of neural networks has prevented recent succ...
research
07/17/2022

Detecting Humans in RGB-D Data with CNNs

We address the problem of people detection in RGB-D data where we levera...
research
06/20/2022

Dynamic Message Propagation Network for RGB-D Salient Object Detection

This paper presents a novel deep neural network framework for RGB-D sali...
research
03/09/2022

Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction

Benefiting from color independence, illumination invariance and location...

Please sign up or login with your details

Forgot password? Click here to reset