Neural Density-Distance Fields
The success of neural fields for 3D vision tasks is now indisputable. Following this trend, several methods aiming for visual localization (e.g., SLAM) have been proposed to estimate distance or density fields using neural fields. However, it is difficult to achieve high localization performance by...
Gespeichert in:
Hauptverfasser: | , , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The success of neural fields for 3D vision tasks is now indisputable.
Following this trend, several methods aiming for visual localization (e.g.,
SLAM) have been proposed to estimate distance or density fields using neural
fields. However, it is difficult to achieve high localization performance by
only density fields-based methods such as Neural Radiance Field (NeRF) since
they do not provide density gradient in most empty regions. On the other hand,
distance field-based methods such as Neural Implicit Surface (NeuS) have
limitations in objects' surface shapes. This paper proposes Neural
Density-Distance Field (NeDDF), a novel 3D representation that reciprocally
constrains the distance and density fields. We extend distance field
formulation to shapes with no explicit boundary surface, such as fur or smoke,
which enable explicit conversion from distance field to density field.
Consistent distance and density fields realized by explicit conversion enable
both robustness to initial values and high-quality registration. Furthermore,
the consistency between fields allows fast convergence from sparse point
clouds. Experiments show that NeDDF can achieve high localization performance
while providing comparable results to NeRF on novel view synthesis. The code is
available at https://github.com/ueda0319/neddf. |
---|---|
DOI: | 10.48550/arxiv.2207.14455 |