IEEE IGARSS 2021 || Brussels, Belgium || July 12–14, 2021 • Physical

TU1.O-16.1

A review of deep-learning techniques for SAR image restoration

Loïc Denis, Université de Lyon, Université Jean-Monnet Saint-Etienne, France; Emanuele Dalsasso, Florence Tupin, Telecom Paris, France

Session:

Deep Learning and SAR Despeckling: An Open and Challenging Issue

Track:

Invited Sessions

Presentation Time:

Tue, 13 Jul, 08:30-09:00 (UTC)
Tue, 13 Jul, 10:30-11:00 Central Europe Summer Time (UTC +2)
Tue, 13 Jul, 16:30-17:00 China Standard Time (UTC +8)
Tue, 13 Jul, 04:30-05:00 Eastern Daylight Time (UTC -4)

Session Co-Chairs:

Florence Tupin, Telecom Paris and Giampaolo Ferraioli, Università degli Studi di Napoli Parthenope

Session Manager:

Axel Deijns

Session TU1.O-16

TU1.O-16.1: A review of deep-learning techniques for SAR image restoration

Loïc Denis, Université de Lyon, Université Jean-Monnet Saint-Etienne, France; Emanuele Dalsasso, Florence Tupin, Telecom Paris, France

TU1.O-16.3: IMPACT OF TRAINING SET DESIGN IN CNN-BASED SAR IMAGE DESPECKLING

Antonio Mazza, Giuseppe Scarpa, Luisa Verdoliva, Giovanni Poggi, University Federico II, Italy

TU1.O-16.4: A MULTI-OBJECTIVE APPROACH FOR MULTI-CHANNEL SAR DESPECKLING

Sergio Vitale, Università degli Studi di Napoli Parthenope, Italy; Hossein Aghababaei, University of Twente, Netherlands; Giampaolo Ferraioli, Vito Pascazio, Gilda Schirinzi, Università degli Studi di Napoli Parthenope, Italy

TU1.O-16.5: COMPARATIVE EVALUATION OF DEEP LEARNING-BASED SAR-OPTICAL IMAGE MATCHING APPROACHES

Lloyd Hughes, Lloyd Hughes Consulting, South Africa; Michael Schmitt, Munich University of Applied Sciences, Germany

TU1.O-16.6: A COHERENT GENERATIVE SCHEME FOR SAR IMAGE REPRESENTATION

Dong-Xiao Yue, Feng Xu, Fudan University, China

A review of deep-learning techniques for SAR image restoration

Quicklinks

Downloads