UnMix-NeRF: Spectral Unmixing Meets Neural Radiance Fields

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Perez, Fabian, Rojas, Sara, Hinojosa, Carlos, Rueda-Chacón, Hoover, Ghanem, Bernard
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911093525315584
author Perez, Fabian
Rojas, Sara
Hinojosa, Carlos
Rueda-Chacón, Hoover
Ghanem, Bernard
author_facet Perez, Fabian
Rojas, Sara
Hinojosa, Carlos
Rueda-Chacón, Hoover
Ghanem, Bernard
contents Neural Radiance Field (NeRF)-based segmentation methods focus on object semantics and rely solely on RGB data, lacking intrinsic material properties. This limitation restricts accurate material perception, which is crucial for robotics, augmented reality, simulation, and other applications. We introduce UnMix-NeRF, a framework that integrates spectral unmixing into NeRF, enabling joint hyperspectral novel view synthesis and unsupervised material segmentation. Our method models spectral reflectance via diffuse and specular components, where a learned dictionary of global endmembers represents pure material signatures, and per-point abundances capture their distribution. For material segmentation, we use spectral signature predictions along learned endmembers, allowing unsupervised material clustering. Additionally, UnMix-NeRF enables scene editing by modifying learned endmember dictionaries for flexible material-based appearance manipulation. Extensive experiments validate our approach, demonstrating superior spectral reconstruction and material segmentation to existing methods. Project page: https://www.factral.co/UnMix-NeRF.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21884
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UnMix-NeRF: Spectral Unmixing Meets Neural Radiance Fields
Perez, Fabian
Rojas, Sara
Hinojosa, Carlos
Rueda-Chacón, Hoover
Ghanem, Bernard
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Signal Processing
Neural Radiance Field (NeRF)-based segmentation methods focus on object semantics and rely solely on RGB data, lacking intrinsic material properties. This limitation restricts accurate material perception, which is crucial for robotics, augmented reality, simulation, and other applications. We introduce UnMix-NeRF, a framework that integrates spectral unmixing into NeRF, enabling joint hyperspectral novel view synthesis and unsupervised material segmentation. Our method models spectral reflectance via diffuse and specular components, where a learned dictionary of global endmembers represents pure material signatures, and per-point abundances capture their distribution. For material segmentation, we use spectral signature predictions along learned endmembers, allowing unsupervised material clustering. Additionally, UnMix-NeRF enables scene editing by modifying learned endmember dictionaries for flexible material-based appearance manipulation. Extensive experiments validate our approach, demonstrating superior spectral reconstruction and material segmentation to existing methods. Project page: https://www.factral.co/UnMix-NeRF.
title UnMix-NeRF: Spectral Unmixing Meets Neural Radiance Fields
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Signal Processing
url https://arxiv.org/abs/2506.21884