# DOOBNet: Deep Object Occlusion Boundary Detection from an Image

arXiv: https://arxiv.org/abs/1806.03772 · HTML: https://mlsanity.com/paper/1806.03772/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2018.

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

- [Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation](https://mlsanity.com/paper/2406.11824/) (2024)
- [RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depth](https://mlsanity.com/paper/2108.00616/) (2021)
- [MT-ORL: Multi-Task Occlusion Relationship Learning](https://mlsanity.com/paper/2108.05722/) (2021)
- [Interactive Occlusion Boundary Estimation through Exploitation of Synthetic Data](https://mlsanity.com/paper/2408.15038/) (2024)
- [Occlusion Boundary and Depth: Mutual Enhancement via Multi-Task Learning](https://mlsanity.com/paper/2505.21231/) (2025)
- [Occlusion-Ordered Semantic Instance Segmentation](https://mlsanity.com/paper/2504.14054/) (2025)
- [RealOOB: A Definition-Consistent Real-World Oriented Occlusion Boundary Benchmark](https://mlsanity.com/paper/2608.30820/) (2026)

## Abstract (arXiv)

Object occlusion boundary detection is a fundamental and crucial research problem in computer vision. This is challenging to solve as encountering the extreme boundary/non-boundary class imbalance during training an object occlusion boundary detector. In this paper, we propose to address this class imbalance by up-weighting the loss contribution of false negative and false positive examples with our novel Attention Loss function. We also propose a unified end-to-end multi-task deep object occlusion boundary detection network (DOOBNet) by sharing convolutional features to simultaneously predict object boundary and occlusion orientation. DOOBNet adopts an encoder-decoder structure with skip connection in order to automatically learn multi-scale and multi-level features. We significantly surpass the state-of-the-art on the PIOD dataset (ODS F-score of .702) and the BSDS ownership dataset (ODS F-score of .555), as well as improving the detecting speed to as 0.037s per image on the PIOD dataset.