给点云加伪标签和可见性信息，就能大幅提升激光语义补全效果。
Exploring Easy Boosts for Lidar Semantic Scene Completion
- 用现成分割器为点云生成语义伪标签，无需改模型结构。
- 结合可见性信息后，多个旧模型性能超越当前最先进系统。
- 方法简单高效，适合想快速提升效果的研究者使用。
本文研究了无需复杂架构调整即可提升激光雷达语义场景补全（SSC）性能的「免费增益」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，能显著提升现有模型表现。通过与理想基准对比，确认高质量语义先验是mIoU提升的主要原因。此外，为输入激光扫描添加区分空区域与未知区域的可见性信息，进一步在所有测试模型上带来次级性能提升。仅通过这些简单增强，旧模型仍具竞争力，甚至超过部分先进系统。代码已公开于https://github.com/astra-vision/SSC-Priors。
原文摘要 · Abstract (English)
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. Our code is available at https://github.com/astra-vision/SSC-Priors.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。