Skip to Main content Skip to Navigation
Conference papers

Empirical Filter Estimation for Subpixel Interpolation and Matching

Bill Triggs 1
1 MOVI - Modeling, localization, recognition and interpretation in computer vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : We study the low-level problem of predicting pixel intensities after subpixel image translations. This is a basic subroutine for image warping and super-resolution, and it has a critical influence on the accuracy of subpixel matching by image correlation. Rather than using traditional frequency-space filtering theory or ad hoc interpolators such as splines, we take an empirical approach, finding optimal subpixel interpolation filters by direct numerical optimization over a large set of training examples. The training set is generated by subsampling larger images at different translations, using subsamplers that mimic the spatial response functions of real pixels. We argue that this gives realistic results, and design filters of various different parametric forms under traditional and robust prediction error metrics. We systematically study the performance of the resulting filters, paying particular attention to the influence of the underlying image sampling regime and the effects of aliasing (“jaggies”). We summarize the results and give practical advice for obtaining subpixel accuracy.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/inria-00548271
Contributor : Thoth Team <>
Submitted on : Monday, December 20, 2010 - 8:42:36 AM
Last modification on : Friday, June 26, 2020 - 4:04:03 PM
Long-term archiving on: : Thursday, June 30, 2011 - 1:44:35 PM

Identifiers

Collections

IMAG | CNRS | INRIA | UGA

Citation

Bill Triggs. Empirical Filter Estimation for Subpixel Interpolation and Matching. 8th International Conference on Computer Vision (ICCV '01), Jul 2001, Vancouver, Canada. pp.550--557, ⟨10.1109/ICCV.2001.937674⟩. ⟨inria-00548271⟩

Share

Metrics

Record views

230

Files downloads

739