Virtual Reality enables the exploration of realistic outer space simulations, where accurate extraterrestrial terrain models are essential features. Due to extreme data retrieval challenges, such models often contain missing values that can hinder the 3D scenarios. We present a surface reconstruction method based on generative diffusion models, and compare it with other void-filling techniques in the task of restoring degraded Martian terrains. Reconstruction outputs were quantitatively assessed by comparing their error and structural consistency with the original values. Our method achieved the best performance on most metrics, suggesting promising prospects for extraterrestrial terrain visualization.

Towards Optimized Mars Terrain Reconstruction Methods for Virtual Reality

Catalano, Giuseppe Lorenzo
First
;
Soccini, Agata Marta
2026-01-01

Abstract

Virtual Reality enables the exploration of realistic outer space simulations, where accurate extraterrestrial terrain models are essential features. Due to extreme data retrieval challenges, such models often contain missing values that can hinder the 3D scenarios. We present a surface reconstruction method based on generative diffusion models, and compare it with other void-filling techniques in the task of restoring degraded Martian terrains. Reconstruction outputs were quantitatively assessed by comparing their error and structural consistency with the original values. Our method achieved the best performance on most metrics, suggesting promising prospects for extraterrestrial terrain visualization.
2026
2026 IEEE Conference on Virtual Reality and 3D User Interfaces (IEEE VR 2026)
Daegu, South Korea
21-25 March 2026
2026 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW)
IEEE
1165
1166
979-8-3195-0530-9
https://ieeexplore.ieee.org/document/11489818
Virtual reality, Artificial intelligence, Mars
Catalano, Giuseppe Lorenzo; Soccini, Agata Marta
File in questo prodotto:
File Dimensione Formato  
Catalano_IEEEVR2026_Poster.pdf

Accesso riservato

Tipo di file: POSTPRINT (VERSIONE FINALE DELL’AUTORE)
Dimensione 5.16 MB
Formato Adobe PDF
5.16 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS 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/2318/2138554
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact