轻量级点云自编码器，用激光雷达数据高效重建3D场景。
LiLa-Net: Lightweight Latent LiDAR Autoencoder for 3D Point Cloud Reconstruction
- 基于跳接结构简化网络，减少编码层数提升效率。
- 在不牺牲性能前提下，实现高精度点云重建。
- 模型泛化性强，可复用于非交通环境的点云重建。
本文提出一种名为LiLa-Net的3D自编码器架构，仅利用真实交通环境中车载Velodyne激光雷达采集的点云数据，实现高效特征编码。系统通过引入跳接连接机制，在不依赖复杂资源的情况下显著提升性能。关键改进包括减少编码器层数并简化跳接结构，同时保持高效的潜在空间表示能力，从而准确重构原始点云。此外，跳接信息与潜在编码之间实现了有效平衡，进一步提升了重建质量。最终，该模型展现出强大的泛化能力，可成功重建原始交通环境以外的物体。
原文摘要 · Abstract (English)
This work proposed a 3D autoencoder architecture, named LiLa-Net, which encodes efficient features from real traffic environments, employing only the LiDAR's point clouds. For this purpose, we have real semi-autonomous vehicle, equipped with Velodyne LiDAR. The system leverage skip connections concept to improve the performance without using extensive resources as the state-of-the-art architectures. Key changes include reducing the number of encoder layers and simplifying the skip connections, while still producing an efficient and representative latent space which allows to accurately reconstruct the original point cloud. Furthermore, an effective balance has been achieved between the information carried by the skip connections and the latent encoding, leading to improved reconstruction quality without compromising performance. Finally, the model demonstrates strong generalization capabilities, successfully reconstructing objects unrelated to the original traffic environment.
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。