SSC-Priors: Exploring Easy Boosts for Lidar Semantic Scene Completion

Tetiana Martyniuk    Jonathan Seele    Alexandre Boulch    Gilles Puy    Renaud Marlet    Raoul de Charette

ICIP 2026

Abstract

This paper investigates "free lunch" strategies to boost the performance of lidar semantic scene completion (SSC) without requiring complex architectural redesigns. We first demonstrate that endowing input point clouds with semantic pseudo-labels from off-the-shelf segmentors significantly improves the performance of existing architectures. By evaluating these models against an oracle, we establish that high-quality semantic priors are a primary driver of mIoU gains. Furthermore, we equip the input lidar scan with visibility information that distinguishes between empty and unknown spaces, which provides a secondary performance boost across the tested architectures. Using these simple enhancements, we observe that older models remain competitive with state-of-the-art systems, and can even outperform them.

BibTeX

@misc{martyniuk2026exploringeasyboostslidar,
      title={Exploring Easy Boosts for Lidar Semantic Scene Completion}, 
      author={Tetiana Martyniuk and Jonathan Seele and Alexandre Boulch and Gilles Puy and Renaud Marlet and Raoul de Charette},
      year={2026},
      eprint={2606.03992},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2606.03992}, 
}