Neural Scanning: Rendering and determining geometry of household objects using Neural Radiance Fields - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Neural Scanning: Rendering and determining geometry of household objects using Neural Radiance Fields

Résumé

In this paper we present a hardware and software framework for Neural Scanning of household objects using Neural Radiance Fields (NeRF). The NeRF technique tries to learn a probabilistic representation of radiance and density, that can be used to render objects and to export objects' geometry. Our framework allows for easy scanning of the objects by rotating the object while using cameras in a static position. The objects we scan are mostly taken from the Yale-CMU-Berkeley (YCB) object set, and we release our scans as part of a public dataset. Supplementary URL: https://robocip-aist.github.io/sii_nerf_scans.
Fichier non déposé

Dates et versions

hal-04112513 , version 1 (31-05-2023)

Identifiants

Citer

Floris Erich, Baptiste Bourreau, Chun Kwang Tan, Guillaume Caron, Yusuke Yoshiyasu, et al.. Neural Scanning: Rendering and determining geometry of household objects using Neural Radiance Fields. 2023 IEEE/SICE International Symposium on System Integration (SII), Jan 2023, Atlanta, United States. pp.1-6, ⟨10.1109/SII55687.2023.10039147⟩. ⟨hal-04112513⟩
55 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More