News

• Mar, 2025: Paper accepted and under publication process in Computers & Graphics.
• Jun, 2025: Website launched.

Abstract

We present a novel approach that combines intrinsic decomposition of outdoor scenes with real-time rendering of new views under unknown illumination. Building on top of the state of the art, our method tackles the challenges of limited information in single-illumination scenarios by introducing pixel-level regularization terms aligning inferred material segmentation labels with albedo consistency estimators. For outdoor illumination, we adopt a physically-based sky model which increases the intrinsic decomposition robustness by relying on a reduced set of expressive parameters. Our approach enables partial retraining of 2DGS/3DGS models to render de-illuminated scenes in real time, with seamless integration into rendering engines for enhanced scene lighting, achieving better decomposition results than the state of the art.

Resources

• ScienceDirect [PDF]

Results

Bibtex

@article{alfonso2025neuralux,
  title={Neuralux: Improving the decomposition of single-illumination multiview outdoor scenes},
  author={Alfonso-Arsuaga, Mario and Castiella-Aguirrezabala, Andrea and Garcia-Gonzalez, Jorge and Bonilla, Jesus and Moreno, Jorge Lopez},
  journal={Computers \& Graphics},
  pages={104279},
  year={2025},
  publisher={Elsevier}
}