Fast multi-scale detail decomposition via accelerated iterative shrinkage
| Autor: | Hicham Badri, Hussein Yahia, Driss Aboutajdine |
|---|---|
| Přispěvatelé: | Geometry and Statistics in acquisition data (GeoStat), Inria Bordeaux - Sud-Ouest, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Laboratoire de Recherche en Informatique et Télécommunications [Rabat] (GSCM-LRIT), Université Mohammed V de Rabat [Agdal] (UM5), CORDI-S grant, ACM SIGGRAPH, University of Rabat |
| Rok vydání: | 2013 |
| Předmět: |
Scale (ratio)
business.industry Computer science ACM: I.: Computing Methodologies/I.4: IMAGE PROCESSING AND COMPUTER VISION/I.4.3: Enhancement/I.4.3.0: Filtering Process (computing) Tone mapping Filter (signal processing) [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing ACM: I.: Computing Methodologies/I.3: COMPUTER GRAPHICS/I.3.6: Methodology and Techniques [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] Decomposition (computer science) ACM: I.: Computing Methodologies/I.4: IMAGE PROCESSING AND COMPUTER VISION/I.4.3: Enhancement Computer vision Artificial intelligence business [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing Algorithm High dynamic range Smoothing Shrinkage |
| Zdroj: | SIGGRAPH ASIA Technical Briefs SIGGRAPH ASIA 2013 SIGGRAPH ASIA 2013, ACM SIGGRAPH, Nov 2013, Hong-Kong, Hong Kong SAR China. ⟨10.1145/2542355.2542397⟩ |
| DOI: | 10.1145/2542355.2542397 |
| Popis: | International audience; 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|