Filter Banks and Multiresolution Transform Layers
Project description
filterbanks: Filter Banks and Multiresolution Transform Layers
filterbanks provides TensorFlow/Keras layers for multiresolution and geometric filter banks.
Capabilities
DCT2D/IDCT2DMultiLevelLiftingDWT1D_KMultiLevelLiftingDWT2D_KMultiLevelLiftingDWT3D_KLapPyrAnalysis/LapPyrSynthesisMonogenicPyramid2DSteerablePyramid2DScattering2DWaveAtoms2DAnalysis/WaveAtoms2DSynthesisWignerVille1Dfilterbanks.tileviewerfor tiling plots
Limitations
- Some layers are analysis-only and do not include a synthesis inverse.
- Exact perfect reconstruction applies only to paired forward/inverse classes where provided.
- Optional viewer and probe utilities may require extra packages such as
matplotlib.
Installation
pip install filterbanks
Transform References
| Transform | Class / Layer | Original paper |
|---|---|---|
| DCT | DCT2D, IDCT2D |
Ahmed, Natarajan, Rao, Discrete Cosine Transform, IEEE Trans. Computers, 1974 |
| Monogenic Pyramid | MonogenicPyramid2D |
Felsberg, Sommer, The monogenic signal, IEEE Trans. Signal Processing, 2001 |
| Laplacian Pyramid | LapPyrAnalysis, LapPyrSynthesis |
Burt, Adelson, The Laplacian Pyramid as a Compact Image Code, IEEE Trans. Communications, 1983 |
| DWT / Wavelets | MultiLevelLiftingDWT1D_K, MultiLevelLiftingDWT2D_K, MultiLevelLiftingDWT3D_K |
Daubechies, Orthonormal bases of compactly supported wavelets, Comm. Pure Appl. Math., 1988 |
| Lifting DWT | MultiLevelLiftingDWT1D_K, MultiLevelLiftingDWT2D_K, MultiLevelLiftingDWT3D_K |
Sweldens, The lifting scheme: A construction of second generation wavelets, SIAM J. Math. Anal., 1998 |
| Steerable Pyramid | SteerablePyramid2D |
Freeman, Adelson, The design and use of steerable filters, IEEE TPAMI, 1991 |
| Curvelet | CurveletTransform2D |
Candès, Donoho, New tight frames of curvelets and optimal representations of objects with piecewise C2 singularities, Comm. Pure Appl. Math., 2004 |
| Contourlet | ContourletTransform2D |
Do, Vetterli, The contourlet transform: an efficient directional multiresolution image representation, IEEE Trans. Image Processing, 2005 |
| Wave Atoms | WaveAtoms2DAnalysis, WaveAtoms2DSynthesis |
Demanet, Ying, Wave atoms and sparsity of oscillatory patterns, Appl. Comput. Harmon. Anal., 2007 |
| Shearlet | ShearletAnalysis2D, ShearletSynthesis2D |
Kutyniok, Labate, Resolution of the wavefront set using continuous shearlets, Trans. Amer. Math. Soc., 2009 |
| Scattering | Scattering2D |
Mallat, Group invariant scattering, Comm. Pure Appl. Math., 2012 |
| Wigner-Ville | WignerVille1D |
Wigner, On the Quantum Correction for Thermodynamic Equilibrium, 1932; Ville, Application de la notion de signal analytique a la determination de l'amplitude et de la frequence instantanee d'un signal, 1948 |
Package-Specific Layers
| Layer | Note |
|---|---|
DWT2DPR |
Exact 2D filter-bank operator form used for validation |
ShearletPRFBLifting |
Trainable shearlet PRFB layers implemented in this package |
DirectionalLiftingNSDL |
Trainable nonsubsampled directional lifting layers implemented in this package |
Minimal Example
import tensorflow as tf
from filterbanks import MultiLevelLiftingDWT2D_K
x = tf.random.normal([1, 64, 64, 1])
layer = MultiLevelLiftingDWT2D_K(levels=2, preset="haar")
pyr = layer(x)
y = layer.synth(*pyr)
print(x.shape, y.shape)
Tiling Viewer
python -m filterbanks.tileviewer.main_viewer --transform contourlet --levels 3 --Ks 4 8 8 --kappas 64 64 64 --H 256 --W 256 --save Figs/contourlet_tiling.png
Citation
This software is released for broad research, educational, and engineering use. If this package helps your work, please cite the following paper:
@misc{tarafdar2026interpretablefrugallearningsystems,
title={Interpretable and Frugal Learning Systems Employing Multiresolution Pyramids and Volterra Kernels},
author={Kishore Kumar Tarafdar},
year={2026},
eprint={2606.15011},
archivePrefix={arXiv},
primaryClass={eess.SP},
url={https://arxiv.org/abs/2606.15011},
}
License
Apache License 2.0. See LICENSE.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file filterbanks-0.0.1.tar.gz.
File metadata
- Download URL: filterbanks-0.0.1.tar.gz
- Upload date:
- Size: 91.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a131dbed411154acae1ef073c93c6896a70353db30c906fa7a367914284a0f7d
|
|
| MD5 |
41d7da2bb3c8eb1311493bfe08e363dd
|
|
| BLAKE2b-256 |
fa7e57a4f2e75114723929649319007c752ed0872083e82d6a189efb9aac1575
|
File details
Details for the file filterbanks-0.0.1-py3-none-any.whl.
File metadata
- Download URL: filterbanks-0.0.1-py3-none-any.whl
- Upload date:
- Size: 116.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
697798e7374bb531808b72c586bc526c2a8563ec47097a4dc7e68b8c9408f138
|
|
| MD5 |
2a05c1d37cf2ccc2bd862d1637180507
|
|
| BLAKE2b-256 |
10054bbdf673f1bb5a61dfd2b1f00e62f3d97db781511640d05cc8dba3ca2fcc
|