Inverse volume rendering poses a significant challenge in reconstructing density and color functions from real-world observations, particularly due to the non injectivity of the problem. This study addresses this issue by introducing a unique criterion to ensure a well-defined solution. We explore the connection between classical regularization, as well as the selection method, and modern neural network approaches. Our methodology integrates minimum support regularization with a novel technique to achieve sharper density estimates, complemented by a georeferencing pipeline that aligns reconstructed point clouds with planar cartographic data, specifically suited for urban sutanability.

Neural radiance fields as a regularization approach to inverse volume rendering

PEDEMONTE, DANIELE
2025

Abstract

Inverse volume rendering poses a significant challenge in reconstructing density and color functions from real-world observations, particularly due to the non injectivity of the problem. This study addresses this issue by introducing a unique criterion to ensure a well-defined solution. We explore the connection between classical regularization, as well as the selection method, and modern neural network approaches. Our methodology integrates minimum support regularization with a novel technique to achieve sharper density estimates, complemented by a georeferencing pipeline that aligns reconstructed point clouds with planar cartographic data, specifically suited for urban sutanability.
19-set-2025
Inglese
BENVENUTO, FEDERICO
BETTIN, SANDRO
Università degli studi di Genova
File in questo prodotto:
File Dimensione Formato  
phdunige_4233143.pdf

accesso aperto

Dimensione 2.31 MB
Formato Adobe PDF
2.31 MB Adobe PDF Visualizza/Apri

I documenti in UNITESI sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.14242/295855
Il codice NBN di questa tesi è URN:NBN:IT:UNIGE-295855