Mitigating non-Lambertian surfaces issues in Stereo Matching with Neural Radiance Fields

Costanzino, Alex (2022) Mitigating non-Lambertian surfaces issues in Stereo Matching with Neural Radiance Fields. [Laurea magistrale], Università di Bologna, Corso di Studio in Artificial intelligence [LM-DM270]
Documenti full-text disponibili:
[img] Documento PDF (Thesis)
Disponibile con Licenza: Salvo eventuali più ampie autorizzazioni dell'autore, la tesi può essere liberamente consultata e può essere effettuato il salvataggio e la stampa di una copia per fini strettamente personali di studio, di ricerca e di insegnamento, con espresso divieto di qualunque utilizzo direttamente o indirettamente commerciale. Ogni altro diritto sul materiale è riservato

Download (2MB)


Depth estimation from images has long been regarded as a preferable alternative compared to expensive and intrusive active sensors, such as LiDAR and ToF. The topic has attracted the attention of an increasingly wide audience thanks to the great amount of application domains, such as autonomous driving, robotic navigation and 3D reconstruction. Among the various techniques employed for depth estimation, stereo matching is one of the most widespread, owing to its robustness, speed and simplicity in setup. Recent developments has been aided by the abundance of annotated stereo images, which granted to deep learning the opportunity to thrive in a research area where deep networks can reach state-of-the-art sub-pixel precision in most cases. Despite the recent findings, stereo matching still begets many open challenges, two among them being finding pixel correspondences in presence of objects that exhibits a non-Lambertian behaviour and processing high-resolution images. Recently, a novel dataset named Booster, which contains high-resolution stereo pairs featuring a large collection of labeled non-Lambertian objects, has been released. The work shown that training state-of-the-art deep neural network on such data improves the generalization capabilities of these networks also in presence of non-Lambertian surfaces. Regardless being a further step to tackle the aforementioned challenge, Booster includes a rather small number of annotated images, and thus cannot satisfy the intensive training requirements of deep learning. This thesis work aims to investigate novel view synthesis techniques to augment the Booster dataset, with ultimate goal of improving stereo matching reliability in presence of high-resolution images that displays non-Lambertian surfaces.

Tipologia del documento
Tesi di laurea (Laurea magistrale)
Autore della tesi
Costanzino, Alex
Relatore della tesi
Correlatore della tesi
Corso di studio
Ordinamento Cds
Parole chiave
stereo matching,neural radiance fields,computer vision,computer graphics,non-lambertian surface,novel view synthesis,deep learning,raft,disparity,depth,machine learning,nerf,semi-global matching,sgm,triangulation,booster dataset,supervised learning
Data di discussione della Tesi
6 Ottobre 2022

Altri metadati

Statistica sui download

Gestione del documento: Visualizza il documento