Embedding Blake-Zisserman Regularization in Unfolded Proximal Neural Networks for Enhanced Edge Detection - CEA - Université Paris-Saclay
Preprints, Working Papers, ... Year : 2024

Embedding Blake-Zisserman Regularization in Unfolded Proximal Neural Networks for Enhanced Edge Detection

Abstract

In this paper, we present a new edge detection model based on proximal unfolded neural networks. The architecture relies on unfolding proximal Blake-Zisserman iterations, leading to a composition of two blocks: a smoothing block and an edge detection block. We show through simulations that the proposed approach efficiently eliminates irrelevant details while retaining key edges and significantly improves performance with respect to state-of-the-art strategies. Additionally, our architecture is significantly lighter than recent learning models designed for edge detection in terms of number of learnable parameters and inference time.
Fichier principal
Vignette du fichier
SPL_2025_v1.pdf (1.82 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04771534 , version 1 (07-11-2024)

Identifiers

  • HAL Id : hal-04771534 , version 1

Cite

Hoang Trieu Vy Le, Marion Foare, Audrey Repetti, Nelly Pustelnik. Embedding Blake-Zisserman Regularization in Unfolded Proximal Neural Networks for Enhanced Edge Detection. 2024. ⟨hal-04771534⟩
0 View
0 Download

Share

More