Reconstructing group wavelet transform from feature maps with a reproducing kernel iteration
Not on the map. Why?
Abstract (arXiv)
In this paper we consider the problem of reconstructing an image that is downsampled in the space of its SE(2) wavelet transform, which is motivated by classical models of simple cells receptive fields and feature preference maps in primary visual cortex. We prove that, whenever the problem is solvable, the reconstruction can be obtained by an elementary project and replace iterative scheme based on the reproducing kernel arising from the group structure, and show numerical results on real images.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 7 of its 82 references that are in the map. First posted on arXiv 1 Oct 2021.
Builds on
7 of 82 references.
References · 7
- 2020Roto-Translation Equivariant Convolutional Networks: Application to Histopathology Image Analysiscited by 32
- 2017Normative theory of visual receptive fieldscited by 15
- 2017A geometric model of multi-scale orientation preference maps via Gabor functionscited by 4
- 2014The constitution of visual perceptual units in the functional architecture of V1cited by 3
- 2018From receptive profiles to a metric model of V1cited by 2
- 2015Geometry and dimensionality reduction of feature spaces in primary visual cortexcited by 1
- 2019KerCNNs: biologically inspired lateral connections for classification of corrupted imagescited by 1
Built on by
Not cited yet.