Abstract
In this paper we address the problem of establishing correspondences between different instances of the same object. The problem is posed as finding the geometric transformation that aligns a given image pair. We use a convolutional neural network (CNN) to directly regress the parameters of the transformation model. The alignment problem is defined in the setting where an unordered set of semantic key-points per image are available, but, without the correspondence information. To this end we propose a novel loss function based on cyclic consistency that solves this 2D point set registration problem by inferring the optimal geometric transformation model parameters. We train and test our approach on a standard benchmark dataset Proposal-Flow (PF-PASCAL)[8]. The proposed approach achieves state-of-the-art results demonstrating the effectiveness of the method. In addition, we show our approach further benefits from additional training samples in PF-PASCAL generated by using category level information.
Original language | English |
---|---|
Title of host publication | 2019 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV) |
Publisher | IEEE |
Pages | 1061-1069 |
Number of pages | 9 |
ISBN (Electronic) | 9781728119755 |
DOIs | |
Publication status | Published - 4 Mar 2019 |
MoE publication type | A4 Conference publication |
Event | IEEE Winter Conference on Applications of Computer Vision - Waikoloa Village, United States Duration: 7 Jan 2019 → 11 Jan 2019 Conference number: 19 |
Conference
Conference | IEEE Winter Conference on Applications of Computer Vision |
---|---|
Abbreviated title | WACV |
Country/Territory | United States |
City | Waikoloa Village |
Period | 07/01/2019 → 11/01/2019 |