Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

11-2019

Abstract

In this paper, we propose a novel iterative multi-task framework to complete the segmentation mask of an occluded vehicle and recover the appearance of its invisible parts. In particular, firstly, to improve the quality of the segmentation completion, we present two coupled discriminators that introduce an auxiliary 3D model pool for sampling authentic silhouettes as adversarial samples. In addition, we propose a two-path structure with a shared network to enhance the appearance recovery capability. By iteratively performing the segmentation completion and the appearance recovery, the results will be progressively refined. To evaluate our method, we present a dataset, Occluded Vehicle dataset, containing synthetic and real-world occluded vehicle images. Based on this dataset, we conduct comparison experiments and demonstrate that our model outperforms the state-of-the-arts in both tasks of recovering segmentation mask and appearance for occluded vehicles. Moreover, we also demonstrate that our appearance recovery approach can benefit the occluded vehicle tracking in real-world videos.

Keywords

Invisible parts, Real world videos, Recovery capabilities, Segmentation masks, Shared network, State of the art, Vehicle images, Vehicle segmentation

Discipline

Databases and Information Systems

Research Areas

Information Systems and Management

Publication

Proceedings of the 17th IEEE/CVF International Conference on Computer Vision, Seoul, South Korea, 2019 October 27- Nov 2

First Page

7617

Last Page

7626

ISBN

9781728148038

Identifier

10.1109/ICCV.2019.00771

Publisher

IEEE

City or Country

New Jersey

Additional URL

http://doi.org/10.1109/ICCV.2019.00771

Download

Share

COinS