TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

CNN-based Cross-dataset No-reference Image Quality Assessment

Tutkimustuotosvertaisarvioitu

Yksityiskohdat

AlkuperäiskieliEnglanti
Otsikko2019 International Conference on Computer Vision Workshop, ICCVW 2019
KustantajaIEEE
Sivut3913-3921
Sivumäärä9
ISBN (elektroninen)978-1-7281-5023-9
ISBN (painettu)978-1-7281-5024-6
DOI - pysyväislinkit
TilaJulkaistu - 2019
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaIEEE International Conference on Computer Vision Workshops -
Kesto: 1 tammikuuta 1900 → …

Julkaisusarja

NimiIEEE International Conference on Computer Vision workshops
ISSN (painettu)2473-9936
ISSN (elektroninen)2473-9944

Conference

ConferenceIEEE International Conference on Computer Vision Workshops
Ajanjakso1/01/00 → …

Tiivistelmä

Recent works on no-reference image quality assessment (NR-IQA) have reported good performance for various datasets. However, they suffer from significant performance drops in cross-dataset evaluations which indicates poor generalization power. We propose a Siamese architecture and training procedures for cross-dataset deep NR-IQA that achieves clearly better performance. Moreover, we show that the architecture can be further boosted by i) pre-training with a large aesthetics dataset and ii) adding low-level quality cues, sharpness, tone and colourfulness, as additional features.

Julkaisufoorumi-taso

Latausten tilastot

Ei tietoja saatavilla