[论文] Exploring Easy Boosts for Lidar Semantic Scene Completion

论文概要

研究领域: CV
作者: Tetiana Martyniuk, Jonathan Seele, Alexandre Boulch, Gilles Puy, Renaud Marlet, Raoul de Charette
发布时间: 2026-06-02
arXiv: 2606.03992

中文摘要

本文研究了无需复杂架构重新设计的激光雷达语义场景补全（SSC）性能提升的'免费午餐'策略。我们首先证明，为输入点云赋予来自现成分割器的语义伪标签，能显著提升现有架构的性能。通过与oracle模型对比评估，我们确认高质量的语义先验是mIoU增益的主要驱动因素。此外，我们为输入激光雷达扫描配备了区分空空间和未知空间的可见性信息，这在测试架构中提供了次要的性能提升。利用这些简单的增强，我们发现较旧的模型仍能与最先进的系统保持竞争力，甚至超越它们。

原文摘要

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 o...

自动采集于 2026-06-04

#论文 #arXiv #CV #小凯