Adding graph-Laplacian band-power matching to the training loss improves long-horizon autoregressive forecasting of chaotic flows on unstructured meshes.
Perturbation of the Eigenvectors of the Graph Laplacian: Application to Image Denoising
1 Pith paper cite this work, alongside 2 external citations. Polarity classification is still indexing.
1
Pith paper citing it
2
external citations · Pith
abstract
The original contributions of this paper are twofold: a new understanding of the influence of noise on the eigenvectors of the graph Laplacian of a set of image patches, and an algorithm to estimate a denoised set of patches from a noisy image. The algorithm relies on the following two observations: (1) the low-index eigenvectors of the diffusion, or graph Laplacian, operators are very robust to random perturbations of the weights and random changes in the connections of the patch-graph; and (2) patches extracted from smooth regions of the image are organized along smooth low-dimensional structures in the patch-set, and therefore can be reconstructed with few eigenvectors. Experiments demonstrate that our denoising algorithm outperforms the denoising gold-standards.
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Scale-Aware Learning of Chaotic Dynamics on Unstructured Meshes via Binned Spectral Losses
Adding graph-Laplacian band-power matching to the training loss improves long-horizon autoregressive forecasting of chaotic flows on unstructured meshes.