Neural Scanning: Rendering and determining geometry of household objects using Neural Radiance Fields
Jan 17, 2023·
,
,
,
,
·
0 min read
Floris Erich
Baptiste BOURREAU
Chun Kwang Tan
Guillaume Caron
Yusuke Yoshiyasu
Noriaki Ando
Abstract
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.
Type
Publication
IEEE/SICE International Symposium on System Integration
Authors
Fullstack Engineer
I am currently working as full stack developer in the DEDALUS group. I’m now learning more about J2E and backend technologies (JPA / Hibernate). During my works, I specialized on the Android platform. I also have a good experience in Angular as well as C#, C++ and Qt for the GUI part. I have a strong interest in the medical field in which I would like to use all my skills acquired so far.