RGB-D video mirror detection

Xu, Mingchen, Herbert, Peter, Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680, Ji, Ze ORCID: https://orcid.org/0000-0002-8968-9902 and Wu, Jing ORCID: https://orcid.org/0000-0001-5123-9861 2025. RGB-D video mirror detection. Presented at: WACV 2025, Tucson, Arizona, 28 February - 04 March 2025. 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE, pp. 9640-9649. 10.1109/WACV61041.2025.00933

Preview

PDF - Accepted Post-Print Version Download (4MB) | Preview

Abstract

Mirror detection aims to identify mirror areas in a scene, with recent methods either integrating depth information (RGB-D) or making use of temporal information (video). However, utilizing both data is still under-explored due to the lack of a high-quality dataset and an effective method for the RGB-D Video Mirror Detection (DVMD) problem. To the best of our knowledge, this is the first work to address the DVMD problem. To exploit depth and temporal information in mirror segmentation, we first construct a large-scale RGB-D Video Mirror Detection Dataset (DVMD-D), which contains 17977 RGB-D images from 273 diverse videos. We further develop a novel model, named DVMDNet, which can first locate the mirrors based on triple consistencies: local consistency, cross-modality consistency and global consistency, and then refine the mirror boundaries through content discontinuity, taking the temporal information within videos into account. We conduct a comparative study on the DVMD dataset, evaluating 12 state-of-the-art models (including single-image mirror detection, single-image glass detection, RGB-D mirror detection, video shadow detection, video glass detection, and video mirror detection methods). Code is available from https://github.com/UpChen/2025_DVMDNet.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Schools > Engineering Schools > Computer Science & Informatics
Publisher:	IEEE
ISBN:	9798331510831
ISSN:	2472-6737
Date of First Compliant Deposit:	6 January 2025
Date of Acceptance:	28 October 2024
Last Modified:	29 Apr 2025 09:50
URI:	https://orca.cardiff.ac.uk/id/eprint/175010

Actions (repository staff only)

Edit Item