2020
DOI: 10.48550/arxiv.2008.00230
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

RGB-D Salient Object Detection: A Survey

Tao Zhou,
Deng-Ping Fan,
Ming-Ming Cheng
et al.
Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
3
1

Relationship

2
2

Authors

Journals

citations
Cited by 4 publications
(3 citation statements)
references
References 90 publications
(365 reference statements)
0
3
0
Order By: Relevance
“…As in Fig. 2 b), existing RGB-D SOD models mainly rely on extracting salient features from RGB image and depth map respectively, and then fuse them in the early or late network stages [46]. Following this trend, earlier work [3] proposes to concatenate RGB-D pairs as 4-channel inputs for salient object detection.…”
Section: Related Workmentioning
confidence: 99%
“…As in Fig. 2 b), existing RGB-D SOD models mainly rely on extracting salient features from RGB image and depth map respectively, and then fuse them in the early or late network stages [46]. Following this trend, earlier work [3] proposes to concatenate RGB-D pairs as 4-channel inputs for salient object detection.…”
Section: Related Workmentioning
confidence: 99%
“…[15] introduced a depth distiller to transfer the depth knowledge from the depth stream to the RGB stream to achieve a lightweight architecture without use of depth data at test time. A comprehensive survey can be found in [44].…”
Section: Rgb-d Saliency Detectionmentioning
confidence: 99%
“…Discussing these works in detail is beyond the scope of this article. Please refer to the online benchmark (http://dpfan.net/d3netbenchmark/) and the latest survey [76] for more details.…”
Section: • Deep Modelsmentioning
confidence: 99%