arXiv Open Access 2020

Structured and Localized Image Restoration

Thomas Eboli Alex Nowak-Vila Jian Sun Francis Bach Jean Ponce +1 lainnya

Lihat Sumber

Abstrak

We present a novel approach to image restoration that leverages ideas from localized structured prediction and non-linear multi-task learning. We optimize a penalized energy function regularized by a sum of terms measuring the distance between patches to be restored and clean patches from an external database gathered beforehand. The resulting estimator comes with strong statistical guarantees leveraging local dependency properties of overlapping patches. We derive the corresponding algorithms for energies based on the mean-squared and Euclidean norm errors. Finally, we demonstrate the practical effectiveness of our model on different image restoration problems using standard benchmarks.

Topik & Kata Kunci

cs.LG cs.CV stat.ML

Penulis (6)

Thomas Eboli

Alex Nowak-Vila

Jian Sun

Francis Bach

Jean Ponce

Alessandro Rudi

Format Sitasi

APA MLA BibTeX

Eboli, T., Nowak-Vila, A., Sun, J., Bach, F., Ponce, J., Rudi, A. (2020). Structured and Localized Image Restoration. https://arxiv.org/abs/2006.09261

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2020
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓