S&CNet: Monocular Depth Completion for Autonomous Systems and 3D Reconstruction
This work addresses depth completion for autonomous systems and 3D reconstruction, offering an incremental improvement in efficiency.
The paper tackles dense depth completion for autonomous systems and 3D reconstruction by proposing S&CNet, a lightweight network that achieves competitive accuracy on the KITTI dataset while being almost four times faster than existing methods.
Dense depth completion is essential for autonomous systems and 3D reconstruction. In this paper, a lightweight yet efficient network (S\&CNet) is proposed to obtain a good trade-off between efficiency and accuracy for the dense depth completion. A dual-stream attention module (S\&C enhancer) is introduced to measure both spatial-wise and the channel-wise global-range relationship of extracted features so as to improve the performance. A coarse-to-fine network is designed and the proposed S\&C enhancer is plugged into the coarse estimation network between its encoder and decoder network. Experimental results demonstrate that our approach achieves competitive performance with existing works on KITTI dataset but almost four times faster. The proposed S\&C enhancer can be plugged into other existing works and boost their performance significantly with a negligible additional computational cost.