| Titre : |
Model based Deep Learning for computational imaging : application to robust multimodal 3D imaging |
| Type de document : |
document électronique |
| Auteurs : |
Ouarda Mekerri, Auteur ; Ilhem Meroua Kaci, Auteur ; Abderrahim Halimi, Directeur de thèse ; Taghi, Mohamed Oussaid, Directeur de thèse |
| Editeur : |
[S.l.] : [s.n.] |
| Année de publication : |
2025 |
| Importance : |
1 fichier PDF (14 Mo) |
| Note générale : |
Mode d'accès : accès au texte intégral par intranet.
Mémoire de Projet de Fin d’Études : Electronique : Alger, École Nationale Polytechnique : 2025
Bibliogr. p. 93-95 |
| Langues : |
Anglais (eng) |
| Mots-clés : |
Depth map
Point cloud
Single photon Lidar
Dtof
Robust
Photon sparsity |
| Index. décimale : |
PN00925 |
| Résumé : |
3D imaging is critical in applications requiring precise spatial detail. Among available technologies, LiDAR sensors are particularly prized for their accuracy and reliability. However, in realistic conditions, their performance is usually compromised by photon noise and sparse, low-resolution measurements.
To overcome these limitations, we introduce a deep learning approach with multiscale processing to produce high-quality depth reconstructions despite low-quality input data. Tested on simulated LiDAR datasets, the method has notable improvements in accuracy and robustness. |
Model based Deep Learning for computational imaging : application to robust multimodal 3D imaging [document électronique] / Ouarda Mekerri, Auteur ; Ilhem Meroua Kaci, Auteur ; Abderrahim Halimi, Directeur de thèse ; Taghi, Mohamed Oussaid, Directeur de thèse . - [S.l.] : [s.n.], 2025 . - 1 fichier PDF (14 Mo).
Mode d'accès : accès au texte intégral par intranet.
Mémoire de Projet de Fin d’Études : Electronique : Alger, École Nationale Polytechnique : 2025
Bibliogr. p. 93-95 Langues : Anglais ( eng)
| Mots-clés : |
Depth map
Point cloud
Single photon Lidar
Dtof
Robust
Photon sparsity |
| Index. décimale : |
PN00925 |
| Résumé : |
3D imaging is critical in applications requiring precise spatial detail. Among available technologies, LiDAR sensors are particularly prized for their accuracy and reliability. However, in realistic conditions, their performance is usually compromised by photon noise and sparse, low-resolution measurements.
To overcome these limitations, we introduce a deep learning approach with multiscale processing to produce high-quality depth reconstructions despite low-quality input data. Tested on simulated LiDAR datasets, the method has notable improvements in accuracy and robustness. |
|
Ajouter le résultat dans votre panier Faire une suggestion Affiner la rechercheModel based Deep Learning for computational imaging (2025)
