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

arXiv: https://arxiv.org/abs/1705.03607 · HTML: https://mlsanity.com/paper/1705.03607/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 May 2017.

## Built on by (most cited first, 7 of 7)

- [Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusion](https://mlsanity.com/paper/2103.11832/) (2021)
- [Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection](https://mlsanity.com/paper/2205.07179/) (2022)
- [Salient Object Detection in RGB-D Videos](https://mlsanity.com/paper/2310.15482/) (2023)
- [SoK: Vehicle Orientation Representations for Deep Rotation Estimation](https://mlsanity.com/paper/2112.04421/) (2021)
- [Efficient Fourier Filtering Network with Contrastive Learning for AAV-based Unaligned Bimodal Salient Object Detection](https://mlsanity.com/paper/2411.03728/) (2024)
- [Dynamic Message Propagation Network for RGB-D Salient Object Detection](https://mlsanity.com/paper/2206.09552/) (2022)
- [Hierarchical Cross-modal Transformer for RGB-D Salient Object Detection](https://mlsanity.com/paper/2302.08052/) (2023)

## Abstract (arXiv)

Recently, deep Convolutional Neural Networks (CNN) have demonstrated strong performance on RGB salient object detection. Although, depth information can help improve detection results, the exploration of CNNs for RGB-D salient object detection remains limited. Here we propose a novel deep CNN architecture for RGB-D salient object detection that exploits high-level, mid-level, and low level features. Further, we present novel depth features that capture the ideas of background enclosure and depth contrast that are suitable for a learned approach. We show improved results compared to state-of-the-art RGB-D salient object detection methods. We also show that the low-level and mid-level depth features both contribute to improvements in the results. Especially, F-Score of our method is 0.848 on RGBD1000 dataset, which is 10.7% better than the second place.