GAC-Net_Geometric and attention-based Network for Depth Completion

TL;DR

This paper introduces CGA-Net, a depth completion network that leverages 3D geometric features and attention mechanisms to produce more accurate dense depth maps from sparse LiDAR data, especially in complex scenes.

Contribution

The paper proposes a novel depth completion network combining PointNet++, attention-based feature fusion, and residual learning with CSPN++, advancing the state-of-the-art in depth prediction accuracy.

Findings

Achieves new SOTA on KITTI dataset

Significantly improves depth prediction in complex scenes

Demonstrates robustness to sparse and challenging data

Abstract

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.