A perceptually motivated online benchmark for image matting

The availability of quantitative online benchmarks for low-level vision tasks such as stereo and optical flow has led to significant progress in the respective fields. This paper introduces such a benchmark for image matting. There are three key factors for a successful benchmarking system: (a) a ch...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2009 IEEE Conference on Computer Vision and Pattern Recognition s. 1826 - 1833
Hlavní autoři: Rhemann, Christoph, Rother, Carsten, Jue Wang, Gelautz, Margrit, Kohli, Pushmeet, Rott, Pamela
Médium: Konferenční příspěvek
Jazyk:angličtina
japonština
Vydáno: IEEE 01.06.2009
Témata:
Benchmark testing
Error correction
Image motion analysis
System testing
ISBN:1424439922, 9781424439928
ISSN:1063-6919, 1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The availability of quantitative online benchmarks for low-level vision tasks such as stereo and optical flow has led to significant progress in the respective fields. This paper introduces such a benchmark for image matting. There are three key factors for a successful benchmarking system: (a) a challenging, high-quality ground truth test set; (b) an online evaluation repository that is dynamically updated with new results; (c) perceptually motivated error functions. Our new benchmark strives to meet all three criteria. We evaluated several matting methods with our benchmark and show that their performance varies depending on the error function. Also, our challenging test set reveals problems of existing algorithms, not reflected in previously reported results. We hope that our effort will lead to considerable progress in the field of image matting, and welcome the reader to visit our benchmark at www.aIphamatting.com.
ISBN:1424439922
9781424439928
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2009.5206503