Türkan, MehmetAlain M.Thoreau D.Guillotel P.Guillemot C.2023-06-162023-06-1620159.78E+121522-4880https://doi.org/10.1109/ICIP.2015.7351585https://hdl.handle.net/20.500.14365/3550The Institute of Electrical and Electronics Engineers on Signal Processing SocietyIEEE International Conference on Image Processing, ICIP 2015 -- 27 September 2015 through 30 September 2015 -- 117806We 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. © 2015 IEEE.eninfo:eu-repo/semantics/openAccesscompressionEpitome learningimage factorizationimage up-scalingneighbor-embeddingsuper-resolutionConference Object10.1109/ICIP.2015.73515852-s2.0-84956657854