TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
RGB-D Salient Object Detection	NJU2K	LBE	S-Measure	69.5	# 24
RGB-D Salient Object Detection	NJU2K	LBE	Average MAE	0.153	# 25
RGB-D Salient Object Detection	NJU2K	LBE	max E-Measure	80.3	# 12
RGB-D Salient Object Detection	NJU2K	LBE	max F-Measure	74.8	# 14

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/local-background-enclosure-for-rgb-d-salient/rgb-d-salient-object-detection-on-nju2k)](https://paperswithcode.com/sota/rgb-d-salient-object-detection-on-nju2k?p=local-background-enclosure-for-rgb-d-salient)`

Local Background Enclosure for RGB-D Salient Object Detection

CVPR 2016 · David Feng, Nick Barnes, ShaoDi You, Chris McCarthy ·

Recent work in salient object detection has considered the incorporation of depth cues from RGB-D images. In most cases, depth contrast is used as the main feature. However, areas of high contrast in background regions cause false positives for such methods, as the background frequently contains regions that are highly variable in depth. Here, we propose a novel RGB-D saliency feature. Local Background Enclosure (LBE) captures the spread of angular directions which are background with respect to the candidate region and the object that it is part of. We show that our feature improves over state-of-the-art RGB-D saliency approaches as well as RGB methods on the RGBD1000 and NJUDS2000 datasets.

PDF Abstract