Search: onr:"swepub:oai:research.chalmers.se:b54c03cf-ecad-4293-8136-5af7d41d5f61" >
ZZ-Net: A Universal...
ZZ-Net: A Universal Rotation Equivariant Architecture for 2D Point Clouds
-
- Bökman, Georg, 1994 (author)
- Chalmers tekniska högskola,Chalmers University of Technology,Chalmers University of Technology, Department of Electrical Engineering, Sweden
-
- Kahl, Fredrik, 1972 (author)
- Chalmers tekniska högskola,Chalmers University of Technology,Chalmers University of Technology, Department of Electrical Engineering, Sweden
-
- Flinth, Axel, 1992 (author)
- Umeå universitet,Institutionen för matematik och matematisk statistik,Chalmers University of Technology, Department of Electrical Engineering, Sweden,Chalmers tekniska högskola,Umeå University
-
(creator_code:org_t)
- IEEE Computer Society, 2022
- 2022
- English.
-
In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. - : IEEE Computer Society. - 1063-6919. ; 2022-June, s. 10966-10975
- Related links:
-
https://doi.org/10.1...
-
show more...
-
https://research.cha...
-
https://urn.kb.se/re...
-
show less...
Abstract
Subject headings
Close
- In this paper, we are concerned with rotation equivariance on 2D point cloud data. We describe a particular set of functions able to approximate any continuous rotation equivariant and permutation invariant function. Based on this result, we propose a novel neural network architecture for processing 2D point clouds and we prove its universality for approximating functions exhibiting these symmetries. We also show how to extend the architecture to accept a set of 2D-2D correspondences as indata, while maintaining similar equivariance properties. Experiments are presented on the estimation of essential matrices in stereo vision.
Subject headings
- NATURVETENSKAP -- Matematik -- Beräkningsmatematik (hsv//swe)
- NATURAL SCIENCES -- Mathematics -- Computational Mathematics (hsv//eng)
- NATURVETENSKAP -- Matematik -- Sannolikhetsteori och statistik (hsv//swe)
- NATURAL SCIENCES -- Mathematics -- Probability Theory and Statistics (hsv//eng)
- NATURVETENSKAP -- Matematik -- Matematisk analys (hsv//swe)
- NATURAL SCIENCES -- Mathematics -- Mathematical Analysis (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
Keyword
- Machine learning
- Deep learning architectures and techniques
Publication and Content Type
- kon (subject category)
- ref (subject category)
Find in a library
To the university's database