Fast Multi-Scale Detail Decomposition via Accelerated Iterative Shrinkage - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2013

Fast Multi-Scale Detail Decomposition via Accelerated Iterative Shrinkage

Abstract

We present a fast solution for performing multi-scale detail decomposition. The proposed method is based on an accelerated iterative shrinkage algorithm, able to process high definition color images in real-time on modern GPUs. Our strategy to accelerate the smoothing process is based on the use of first order proximal operators. We use the approximation to both designing suitable shrinkage operators as well as deriving a proper warm-start solution. The method supports full color filtering and can be implemented efficiently and easily on both the CPU and the GPU. We demonstrate the performance of the proposed approach on fast multi-scale detail manipulation of low and high dynamic range images and show that we get good quality results with reduced processing time.
Fichier principal
Vignette du fichier
siggraphasia2013_badri.pdf (10.31 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00860081 , version 1 (10-09-2013)
hal-00860081 , version 2 (11-09-2013)

Identifiers

Cite

Hicham Badri, Hussein Yahia, Driss Aboutajdine. Fast Multi-Scale Detail Decomposition via Accelerated Iterative Shrinkage. SIGGRAPH ASIA 2013, ACM SIGGRAPH, Nov 2013, Hong-Kong, Hong Kong SAR China. ⟨10.1145/2542355.2542397⟩. ⟨hal-00860081v2⟩
787 View
776 Download

Altmetric

Share

Gmail Facebook X LinkedIn More