DarkGS: Learning Neural Illumination and 3D Gaussians Relighting for Robotic Exploration in the Dark
IEEE/RSJ International Conference on Intelligent Robots and Systems 2024 Humans have the remarkable ability to construct consistent mental models of an environment, even under limited or varying levels of illumination. We wish to endow robots with this same capability. In this paper, we tackle the c...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | IEEE/RSJ International Conference on Intelligent Robots and
Systems 2024 Humans have the remarkable ability to construct consistent mental models of
an environment, even under limited or varying levels of illumination. We wish
to endow robots with this same capability. In this paper, we tackle the
challenge of constructing a photorealistic scene representation under poorly
illuminated conditions and with a moving light source. We approach the task of
modeling illumination as a learning problem, and utilize the developed
illumination model to aid in scene reconstruction. We introduce an innovative
framework that uses a data-driven approach, Neural Light Simulators (NeLiS), to
model and calibrate the camera-light system. Furthermore, we present DarkGS, a
method that applies NeLiS to create a relightable 3D Gaussian scene model
capable of real-time, photorealistic rendering from novel viewpoints. We show
the applicability and robustness of our proposed simulator and system in a
variety of real-world environments. |
---|---|
DOI: | 10.48550/arxiv.2403.10814 |