将扩散模型压缩为高效3D激光雷达场景补全方法，速度提升5倍以上。
Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion
- 设计专用蒸馏方法ScoreLiDAR，实现少步采样。
- 在SemanticKITTI上完成时间从30.55秒降至5.37秒（>5倍加速）。
- 引入结构损失，更好保留场景几何结构，适合自动驾驶感知应用。
扩散模型因训练稳定且完成质量高，被用于3D激光雷达场景补全。但其采样速度慢，难以满足自动驾驶对环境感知的实时性要求。本文提出专用于3D激光雷达场景补全的新型蒸馏方法ScoreLiDAR，实现高效且高质量的场景补全。ScoreLiDAR使蒸馏后模型可在显著更少采样步数下完成生成。为提升补全质量，还引入一种新颖的结构损失，该损失包含全局场景项与关键点及其相对配置的点级项，以约束三维结构。大量实验表明，ScoreLiDAR在SemanticKITTI数据集上将每帧完成时间从30.55秒缩短至5.37秒（>5倍加速），并优于当前最优3D激光雷达场景补全模型。代码与模型已公开于https://github.com/happyw1nd/ScoreLiDAR。
原文摘要 · Abstract (English)
Diffusion models have been applied to 3D LiDAR scene completion due to their strong training stability and high completion quality. However, the slow sampling speed limits the practical application of diffusion-based scene completion models since autonomous vehicles require an efficient perception of surrounding environments. This paper proposes a novel distillation method tailored for 3D Li- DAR scene completion models, dubbed ScoreLiDAR, which achieves efficient yet high-quality scene completion. Score- LiDAR enables the distilled model to sample in significantly fewer steps after distillation. To improve completion quality, we also introduce a novel Structural Loss, which encourages the distilled model to capture the geometric structure of the 3D LiDAR scene. The loss contains a scene-wise term constraining the holistic structure and a point-wise term constraining the key landmark points and their relative configuration. Extensive experiments demonstrate that ScoreLiDAR significantly accelerates the completion time from 30.55 to 5.37 seconds per frame (>5x) on SemanticKITTI and achieves superior performance compared to state-of-the-art 3D LiDAR scene completion models. Our model and code are publicly available on https://github.com/happyw1nd/ScoreLiDAR.
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。