Pixel-Pair Occlusion Relationship mAP (P2ORM): Formulation, Inference & Application
Abstract
Inference & Application","We formalize concepts around geometric occlusion in 2D images (i.e., ignoring semantics), and propose a novel unified formulation of both occlusion boundaries and occlusion orientations via a pixel-pair occlusion relation. The former provides a way to generate large-scale accurate occlusion datasets while, based on the latter, we propose a novel method for task-independent pixel-level occlusion relationship estimation from single images. Experiments on a variety of datasets demonstrate that our method outperforms existing ones on this task. To further illustrate the value of our formulation, we also propose a new depth map refinement method that consistently improve the performance of state-of-the-art monocular depth estimation methods.
Cite
Text
Qiu et al. "Pixel-Pair Occlusion Relationship mAP (P2ORM): Formulation, Inference & Application." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58548-8_40Markdown
[Qiu et al. "Pixel-Pair Occlusion Relationship mAP (P2ORM): Formulation, Inference & Application." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/qiu2020eccv-pixelpair/) doi:10.1007/978-3-030-58548-8_40BibTeX
@inproceedings{qiu2020eccv-pixelpair,
title = {{Pixel-Pair Occlusion Relationship mAP (P2ORM): Formulation, Inference & Application}},
author = {Qiu, Xuchong and Xiao, Yang and Wang, Chaohui and Marlet, Renaud},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2020},
doi = {10.1007/978-3-030-58548-8_40},
url = {https://mlanthology.org/eccv/2020/qiu2020eccv-pixelpair/}
}