Skip to Main content Skip to Navigation
Conference papers

Epitomic image factorization via neighbor-embedding

Abstract : We describe a novel epitomic image representation scheme that factors a given image content into a condensed epitome and a low-resolution image to reduce the memory space for images. Given an input image, we construct a condensed epitome such that all image patches can successfully be reconstructed from the factored representation by means of an optimized neighbor-embedding strategy. Under this new scope of epitomic image representations aligned with the manifold sampling assumption, we end up a more generic epitome learning scheme with increased optimality, compactness, and reconstruction stability. We present the performance of the proposed method for image and video up-scaling (super-resolution) while extensions to other image and video processing are straightforward.
Document type :
Conference papers
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download

https://hal.inria.fr/hal-01204755
Contributor : Mehmet Turkan <>
Submitted on : Friday, October 2, 2015 - 10:25:48 PM
Last modification on : Friday, July 10, 2020 - 4:11:29 PM
Long-term archiving on: : Sunday, January 3, 2016 - 10:13:00 AM

File

388-v6sP-121.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01204755, version 1

Citation

Mehmet Turkan, Martin Alain, Dominique Thoreau, Philippe Guillotel, Christine Guillemot. Epitomic image factorization via neighbor-embedding. 2015 IEEE International Conference on Image Processing (IEEE-ICIP), Sep 2015, Quebec City, Canada. ⟨hal-01204755⟩

Share

Metrics

Record views

563

Files downloads

352