arXiv Computer Vision October 19, 2026 By Assaf Shocher

A Unified Theory of Image Scaling: Point Spread Functions, Discrete Kernels, and Scale-Spaces

Read the original on arXiv Computer Vision →

The paper presents a closed‑form system of image‑scaling operators <K_s> that faithfully reproduce optical zoom by leveraging the camera’s point spread function (PSF). These operators compose multiplicatively, form a Moore‑Penrose pseudoinverse pair, and provide a generalized, bidirectional scale‑space that extends beyond conventional Gaussian kernels. The authors validate the model with real captures and simulations, showing improved stability for tasks such as super‑resolution and classification.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv Computer Vision

Sep 28

Scale-invariant Gaussian derivative residual networks

arXiv:2603.02843v2 Announce Type: replace Abstract: Generalisation across image scales remains a fundamental challenge for deep networks, which often fail to handle images at scales not seen during t...

By Andrzej Perzanowski, Tony Lindeberg

computer-vision benchmarks

arXiv AI

Aug 21

Core-KAN: Continuous Vision Kernels with Kolmogorov-Arnold Networks

arXiv:2608. 19817v1 Announce Type: cross Abstract: Conventional convolutional kernels are typically defined on fixed discrete grids, limiting their ability to accommodate heterogeneous local structures.

By Lan Guo, Mengling Li, Haoran Li, Jun Shen, Yuanbo Jiang, Qingguo Zhou, Binbin Yong

arXiv Machine Learning

Jul 27

gp2Scale: A Class of Compactly Supported Non-Stationary Kernels and Distributed Computing for Exact Gaussian Processes on 10 Million Data Points

arXiv:2512. 06143v2 Announce Type: replace Abstract: Despite a large corpus of recent work on scaling up Gaussian processes, a stubborn trade-off between computational speed, prediction and uncertainty quantification accuracy, and customizability persists.

By Marcus M. Noack, Mark D. Risser, Hengrui Luo, Vardaan Tekriwal, Ronald J. Pandolfi

benchmarks

arXiv Machine Learning

Sep 30

Scale Sensitivity in Low-Bit Post-Training Quantization: Curvature of the Quantization Error Landscape

arXiv:2609.37416v1 Announce Type: new Abstract: Post-training quantization (PTQ) methods in the GPTQ family minimize a layer-wise reconstruction error on a uniform grid whose scale must be chosen; th...

By Jonas von Berg, Massimiliano Datres, Carlo Knei{\ss}l, Gitta Kutyniok

llms efficiency

arXiv Machine Learning

Sep 10

A Note on Scaling in Randomly Rotated Quantization and Its Connection to the CDEF +1 Pythagorean Relation

arXiv:2609.08759v1 Announce Type: cross Abstract: Quantization schemes based on randomized rotations have recently received renewed attention, including the roles of MMSE and unbiased reconstruction...

By Uri Erez

efficiency

arXiv Machine Learning

Jul 27

Data eccentricity, asymptotics of Gaussian RBF reproducing kernel Hilbert space, and kernel PCA

arXiv:2607. 21823v1 Announce Type: new Abstract: We show that, up to isotropic scaling, the Gaussian RBF reproducing kernel Hilbert space (RKHS) is asymptotically isometric to Euclidean space in the large bandwidth limit.

By Sergio A. Alvarez

rag

One email a morning, machine-written

Related stories

Scale-invariant Gaussian derivative residual networks

Core-KAN: Continuous Vision Kernels with Kolmogorov-Arnold Networks

gp2Scale: A Class of Compactly Supported Non-Stationary Kernels and Distributed Computing for Exact Gaussian Processes on 10 Million Data Points

Scale Sensitivity in Low-Bit Post-Training Quantization: Curvature of the Quantization Error Landscape

A Note on Scaling in Randomly Rotated Quantization and Its Connection to the CDEF +1 Pythagorean Relation

Data eccentricity, asymptotics of Gaussian RBF reproducing kernel Hilbert space, and kernel PCA