Conference Paper/Proceeding/Abstract 324 views 27 downloads
Effective Video Mirror Detection with Inconsistent Motion Cues
,
Rynson W.H. Lau,
Rynson Lau
2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Pages: 17244 - 17252
Swansea University Authors:
Alex Warren, Gary Tam , Rynson Lau
-
PDF | Accepted Manuscript
Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention).
Download (5.79MB)
DOI (Published version): 10.1109/cvpr52733.2024.01632
Abstract
Image-based mirror detection has recently undergone rapid research due to its significance in applications such as robotic navigation, semantic segmentation and scene re-construction. Recently, VMD-Net was proposed as the first video mirror detection technique, by modeling dual correspondences betwe...
| Published in: | 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
|---|---|
| ISBN: | 979-8-3503-5301-3 979-8-3503-5300-6 |
| ISSN: | 1063-6919 2575-7075 |
| Published: |
IEEE
2024
|
| Online Access: |
Check full text
|
| URI: | https://cronfa.swan.ac.uk/Record/cronfa65886 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract: |
Image-based mirror detection has recently undergone rapid research due to its significance in applications such as robotic navigation, semantic segmentation and scene re-construction. Recently, VMD-Net was proposed as the first video mirror detection technique, by modeling dual correspondences between the inside and outside of the mirror both spatially and temporally. However, this approach is not reliable, as correspondences can occur completely inside or outside of the mirrors. In addition, the proposed dataset VMD-D contains many small mirrors, limiting its applicability to real-world scenarios. To address these problems, we developed a more challenging dataset that includes mirrors of various shapes and sizes at different locations of the frames, providing a better reflection of real-world scenarios. Next, we observed that the motions between the inside and outside of the mirror are often in-consistent. For instance, when moving in front of a mirror, the motion inside the mirror is often much smaller than the motion outside due to increased depth perception. With these observations, we propose modeling inconsistent motion cues to detect mirrors, and a new network with two novel modules. The Motion Attention Module (MAM) ex-plicitly models inconsistent motions around mirrors via optical flow, and the Motion-Guided Edge Detection Module (MEDM) uses motions to guide mirror edge feature learning. Experimental results on our proposed dataset show that our method outperforms state-of-the-arts. The code and dataset are available at ht tps: // gi th ub. com/ AlexAnthonyWarren/MG-VMD. |
|---|---|
| College: |
Faculty of Science and Engineering |
| Funders: |
Alex is supported by a Swansea GTA Research Scholarship. This project is in part supported by a
GRF grant from the Research Grants Council of Hong Kong (Ref.: 11211223). We gratefully acknowledge the support of the HEFCW HERC fund (W21/21HE) for the provision of GPU equipment used in this research. |
| Start Page: |
17244 |
| End Page: |
17252 |