HIGHLIGHTS
- who: Kento Doi and collaborators from the School of Engineering, The University of Tokyo, Tokyo, Japan have published the Article: Detecting Object-Level Scene Changes in Images with Viewpoint Differences Using Graph Matching, in the Journal: (JOURNAL)
- what: The authors propose a robust method for object-level change detection in images with viewpoint differences that utilizes object detection and a graph matching network . The method that is the most related to the approach is the SuperGlue network that was proposed by Sarlin et_al, which is a graph matching network with an attentional GNN and an . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.