用几何注意力提升稀疏激光雷达深度补全效果
GAC-Net_Geometric and attention-based Network for Depth Completion
- 通过PointNet++提取深度图3D全局几何特征
- 融合图像、深度与几何特征，提升边界精度
- 适合自动驾驶中复杂场景的深度补全任务
深度补全是自动驾驶中的关键任务，旨在通过图像引导将稀疏激光雷达深度数据补全为高质量稠密深度图。现有方法通常将深度图视为彩色图像的附加通道，或直接对稀疏数据进行卷积，未能充分挖掘深度图中的三维几何信息，尤其在复杂边界和稀疏区域表现不佳。为此，本文提出结合通道注意力与3D全局特征感知的CGA-Net。主要创新包括：1）利用PointNet++从稀疏深度图中提取全局3D几何特征，增强低线数激光雷达数据的场景感知能力；2）设计基于通道注意力的多模态特征融合模块，高效融合稀疏深度、RGB图像与3D几何特征；3）结合残差学习与CSPN++优化深度细化阶段，进一步提升边缘区域与复杂场景下的补全质量。在KITTI深度补全数据集上的实验表明，CGA-Net显著提升稠密深度图预测精度，达到新的最佳性能（SOTA），并在稀疏与复杂场景中表现出强鲁棒性。
原文摘要 · Abstract (English)
Depth completion is a key task in autonomous driving, aiming to complete sparse LiDAR depth measurements into high-quality dense depth maps through image guidance. However, existing methods usually treat depth maps as an additional channel of color images, or directly perform convolution on sparse data, failing to fully exploit the 3D geometric information in depth maps, especially with limited performance in complex boundaries and sparse areas. To address these issues, this paper proposes a depth completion network combining channel attention mechanism and 3D global feature perception (CGA-Net). The main innovations include: 1) Utilizing PointNet++ to extract global 3D geometric features from sparse depth maps, enhancing the scene perception ability of low-line LiDAR data; 2) Designing a channel-attention-based multimodal feature fusion module to efficiently integrate sparse depth, RGB images, and 3D geometric features; 3) Combining residual learning with CSPN++ to optimize the depth refinement stage, further improving the completion quality in edge areas and complex scenes. Experiments on the KITTI depth completion dataset show that CGA-Net can significantly improve the prediction accuracy of dense depth maps, achieving a new state-of-the-art (SOTA), and demonstrating strong robustness to sparse and complex scenes.
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。