Scholarlink

The rapid adoption of LiDAR sensors in autonomous driving has led to an explosion of LiDAR point cloud (LPC) data, posing substantial challenges for storage and transmission. To address the complexity of large-scale and spatially non-uniform LiDAR point clouds, we introduce a new multimodal and residual-driven scalable framework (MARSNet) for LiDAR point cloud compression (LPCC). Our MARSNet integrates an end-to-end deep network with a residual-aware compression module that leverages multiple modalities. By aligning and jointly encoding point cloud, depth, segmentation, and residual information, the proposed approach generates ultra-low-bit latent representations while preserving fine-grained geometric details. Extensive experimental validations show that MARSNet consistently outperforms 16 advanced LPCC models, achieving superior reconstruction quality at ultra-low bitrates.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

MARSNet: Scalable Deep Coding of LiDAR Point Clouds via Multimodal and Residual Learning

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Yanji Huang,
  • Runnan Huang,
  • Jianlong Zhou,
  • Yingqi Zhuo,
  • Yanshan Li,
  • Miaohui Wang

摘要

The rapid adoption of LiDAR sensors in autonomous driving has led to an explosion of LiDAR point cloud (LPC) data, posing substantial challenges for storage and transmission. To address the complexity of large-scale and spatially non-uniform LiDAR point clouds, we introduce a new multimodal and residual-driven scalable framework (MARSNet) for LiDAR point cloud compression (LPCC). Our MARSNet integrates an end-to-end deep network with a residual-aware compression module that leverages multiple modalities. By aligning and jointly encoding point cloud, depth, segmentation, and residual information, the proposed approach generates ultra-low-bit latent representations while preserving fine-grained geometric details. Extensive experimental validations show that MARSNet consistently outperforms 16 advanced LPCC models, achieving superior reconstruction quality at ultra-low bitrates.