Partager cette page :
Séminaire #9 mardi 06/04/2021 par Julien Mairal - Aliasing is your Ally: End-to-End Super-Resolution from Raw Image Bursts
le 6 avril 2021
ENS Rennes
Intervention de Julien Mairal, chercheur dans l'équipe LEAR de Inria Grenoble, dans le cadre des séminaires du département Informatique et télécommunications.
Aliasing is your Ally: End-to-End Super-Resolution from Raw Image Bursts
This presentation addresses the problem of reconstructing a high-resolution image from multiple lower-resolution snapshots captured from slightly different viewpoints in space and time. Key challenges for solving this super-resolution problem include (i) aligning the input pictures with sub-pixel accuracy, (ii) handling raw (noisy) images for maximal faithfulness to native camera data, and (iii) designing/learning an image prior (regularizer) well suited to the task. We address these three challenges with a hybrid algorithm building on the insight that aliasing is an ally in this setting, with parameters that can be learned end to end, while retaining the interpretability of classical approaches to inverse problems. The effectiveness of our approach is demonstrated on synthetic and real image bursts, setting a new state of the art on several benchmarks and delivering excellent qualitative results on real raw bursts captured by smartphones and prosumer cameras.
De 16h15 à 17h15 en visio-conférence via ce serveur BigBlueButton. Séminaire ouvert à toutes et à tous, élèves et personnel de l'ENS Rennes et extérieurs, tous départements confondus. Obligatoire pour les élèves de 1re et 2e année du département informatique.
This presentation addresses the problem of reconstructing a high-resolution image from multiple lower-resolution snapshots captured from slightly different viewpoints in space and time. Key challenges for solving this super-resolution problem include (i) aligning the input pictures with sub-pixel accuracy, (ii) handling raw (noisy) images for maximal faithfulness to native camera data, and (iii) designing/learning an image prior (regularizer) well suited to the task. We address these three challenges with a hybrid algorithm building on the insight that aliasing is an ally in this setting, with parameters that can be learned end to end, while retaining the interpretability of classical approaches to inverse problems. The effectiveness of our approach is demonstrated on synthetic and real image bursts, setting a new state of the art on several benchmarks and delivering excellent qualitative results on real raw bursts captured by smartphones and prosumer cameras.
De 16h15 à 17h15 en visio-conférence via ce serveur BigBlueButton. Séminaire ouvert à toutes et à tous, élèves et personnel de l'ENS Rennes et extérieurs, tous départements confondus. Obligatoire pour les élèves de 1re et 2e année du département informatique.
- Thématique(s)
- Formation, Recherche - Valorisation
Mise à jour le 31 mars 2021