LLCT: Learnable Linear Canonical Transform Family with Stability for Visual Feature Processing

Abstract

Visual structures are often characterized by directional geometry, local oscillation, and spatial--frequency coupling. To overcome the limitations of conventional spatial convolutions mainly operating on fixed Euclidean coordinates, this article develops the learnable linear canonical transform (LLCT) framework that learns parameters within the linear canonical transform (LCT) family. The framework treats the LCT family as parameterized analytical views spanning spatial, Fourier, and intermediate linear canonical representations. The framework has the following two complementary modes. The Linear Canonical Riesz Transform (LCRT) mode combines learned linear canonical coordinates with regularized Riesz-type directional responses at sites chosen for geometric and local-structural refinement. The learnable LCT mode provides the integrated responses for latent feature sites. We establish the parameter stability of the LCT representation under admissible perturbations of the canonical matrices. Both modes use chirp multiplication and the fast Fourier transform (FFT) to preserve feature dimensions and support automatic differentiation. Experiments on crack segmentation and single-image deraining evaluate the above two modes with multiple backbones. On four segmentation backbones, the full LCRT mode gives the highest reported point estimates of F1 and IoU for the crack class among the tested variants. The learnable LCT mode gives higher values in 30 of 32 paired PSNR and SSIM measurements across four deraining backbones and four datasets. In ablation studies, the full model has the highest reported PSNR and SSIM among five tested configurations.

Analysis of Delay Differential Equations Using the Offset Linear Canonical Transform
Gita Rani Mahato, Manab Kundu
arXiv30 Sep 2026PreprintCC BY 4.0Full textMathematical physicsarXiv
Particle-Number-Preserving Quantum Signal Processing for Thermal Properties: Canonical-Ensemble Estimation and Grand-Canonical Reconstruction
Taehee Ko, Sungbin Lim, Sangkook Choi
arXiv7 Oct 2026PreprintarXiv licenceFull textNumerical analysis & scientific computing Quantum physics & quantum informationarXiv
From Common Information to Canonical Correlation Analysis and Beyond: Bridging Information Theory, Signal Processing, and Machine Learning
Paris A. Karakasis, Walid Saad
arXiv20 Oct 2026PreprintCC BY 4.0Full textStatisticsarXiv
Inverting the geodesic ray transform with finite measurements: stability and reconstruction
Yernat M. Assylbekov
arXiv30 Sep 2026PreprintarXiv licenceFull textAnalysis & PDEs Geometry & topologyarXiv
Stability of the Markov-Krein Transform Under Classical Convolutions
Pierre Mergny
arXiv13 Oct 2026PreprintCC0Full textMathematical physics ProbabilityarXiv

Cite

BibTeX RIS

BibTeX

@misc{fu2026llct,
  title = {{LLCT: Learnable Linear Canonical Transform Family with Stability for Visual Feature Processing}},
  author = {Zunwei Fu and Zhen Wang and Dachun Yang and Shuhui Yang},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.20295},
  eprint = {2610.20295},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.20295},
}

RIS

TY  - UNPB
TI  - LLCT: Learnable Linear Canonical Transform Family with Stability for Visual Feature Processing
AU  - Zunwei Fu
AU  - Zhen Wang
AU  - Dachun Yang
AU  - Shuhui Yang
PY  - 2026
DA  - 2026/10/14
PB  - arXiv
DO  - 10.48550/arxiv.2610.20295
UR  - https://arxiv.org/abs/2610.20295
AB  - Visual structures are often characterized by directional geometry, local oscillation, and spatial--frequency coupling. To overcome the limitations of conventional spatial convolutions mainly operating on fixed Euclidean coordinates, this article develops the learnable linear canonical transform (LLCT) framework that learns parameters within the linear canonical transform (LCT) family. The framework treats the LCT family as parameterized analytical views spanning spatial, Fourier, and intermediate linear canonical representations. The framework has the following two complementary modes. The Linear Canonical Riesz Transform (LCRT) mode combines learned linear canonical coordinates with regularized Riesz-type directional responses at sites chosen for geometric and local-structural refinement. The learnable LCT mode provides the integrated responses for latent feature sites. We establish the parameter stability of the LCT representation under admissible perturbations of the canonical matrices. Both modes use chirp multiplication and the fast Fourier transform (FFT) to preserve feature dimensions and support automatic differentiation. Experiments on crack segmentation and single-image deraining evaluate the above two modes with multiple backbones. On four segmentation backbones, the full LCRT mode gives the highest reported point estimates of F1 and IoU for the crack class among the tested variants. The learnable LCT mode gives higher values in 30 of 32 paired PSNR and SSIM measurements across four deraining backbones and four datasets. In ablation studies, the full model has the highest reported PSNR and SSIM among five tested configurations.
ER  -

Abstract

Related

Cite