arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.18092cs.CVcs.AIcs.RO
收藏

DiffSSC:基于去噪扩散概率模型的语义激光雷达扫描补全

DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Models

Autonomous Intelligent Systems group, Computer Science Institute VI – Intelligent Systems and Robotics – and the Center for Robotics and the Lamarr Institute for Machine Learning and Artificial Intelligence, University of Bonn, Germany(自主智能系统组,计算机科学研究所VI——智能系统与机器人——和机器人中心以及拉马尔人工智能与机器学习研究所,波恩大学,德国)

Helin Cao, Sven Behnke

AI总结:

本文提出DiffSSC,利用去噪扩散概率模型在点云和语义空间分别进行加噪去噪,以语义激光雷达点云为条件输入并设计正则化损失,实现语义场景补全,在自动驾驶数据集上达到最先进性能。

摘要:

感知系统在自动驾驶中扮演着关键角色,它融合了多种传感器和相应的计算机视觉算法。3D激光雷达传感器被广泛用于捕获车辆周围环境的稀疏点云。然而,由于这些点云的稀疏性以及缺乏语义信息,此类系统难以感知场景中的遮挡区域和空隙。为了应对这些挑战,语义场景补全(SSC)在给定原始激光雷达测量的情况下,联合预测场景中未观测到的几何结构和语义,旨在获得更完整的场景表示。基于扩散模型在图像生成和超分辨率任务中取得的令人鼓舞的成果,我们提出将其扩展到SSC,通过在点和语义空间中分别实施加噪和去噪扩散过程来实现。为了控制生成过程,我们采用语义激光雷达点云作为条件输入,并设计局部和全局正则化损失以稳定去噪过程。我们在自动驾驶数据集上评估了我们的方法,它在SSC任务上达到了最先进的性能,超越了大多数现有方法。

英文摘要:

Perception systems play a crucial role in autonomous driving, incorporating multiple sensors and corresponding computer vision algorithms. 3D LiDAR sensors are widely used to capture sparse point clouds of the vehicle's surroundings. However, such systems struggle to perceive occluded areas and gaps in the scene due to the sparsity of these point clouds and their lack of semantics. To address these challenges, Semantic Scene Completion (SSC) jointly predicts unobserved geometry and semantics in the scene given raw LiDAR measurements, aiming for a more complete scene representation. Building on promising results of diffusion models in image generation and super-resolution tasks, we propose their extension to SSC by implementing the noising and denoising diffusion processes in the point and semantic spaces individually. To control the generation, we employ semantic LiDAR point clouds as conditional input and design local and global regularization losses to stabilize the denoising process. We evaluate our approach on autonomous driving datasets, and it achieves state-of-the-art performance for SSC, surpassing most existing methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑