Novel Arc-Cost Functions and Seed Relevance Estimations for Compact and Accurate Superpixels - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Journal of Mathematical Imaging and Vision Année : 2023

Novel Arc-Cost Functions and Seed Relevance Estimations for Compact and Accurate Superpixels

Résumé

On the verge of superpixel methods exploiting saliency information, the Superpixels through Iterative CLEarcutting (SICLE) framework has reported fast and accurate superpixel delineation. It is composed of three steps: (i) seed oversampling; (ii) superpixel generation; and (iii) seed removal. It starts from (i) and applies several iterations of (ii) and (iii) until reaching the desired superpixel quantity. In this work, we improve SICLE such that it can now generate compact superpixels with accurate delineation. We exploit differential computation and propose several novel functions for steps (ii) and (iii) for proper saliency incorporation, compact superpixel generation, and improvement in speed and delineation. Results show that, with our proposals, SICLE achieves state-of-the-art performance in delineation and speed whenever saliency is absent with on-par compacity. When an accurate saliency map is provided, its performance improves significantly and requires only two iterations for segmentation.
Fichier principal
Vignette du fichier
Belem - JMIV 2023 - Superpixels.pdf (5.66 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04345100 , version 1 (14-12-2023)

Identifiants

Citer

Felipe C Belém, Isabela B Barcelos, Leonardo M João, Benjamin Perret, Jean Cousty, et al.. Novel Arc-Cost Functions and Seed Relevance Estimations for Compact and Accurate Superpixels. Journal of Mathematical Imaging and Vision, 2023, 65 (5), pp.770-786. ⟨10.1007/s10851-023-01156-9⟩. ⟨hal-04345100⟩
19 Consultations
7 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More