Confidence Guided Depth Completion Network
This work addresses depth estimation for applications like autonomous driving, but it is incremental as it builds on existing image-guided methods.
The paper tackles depth completion by proposing a two-stage network that refines depth maps using confidence maps, achieving competitive performance on the KITTI benchmark with much faster computation time.
The paper proposes an image-guided depth completion method to estimate accurate dense depth maps with fast computation time. The proposed network has two-stage structure. The first stage predicts a first depth map. Then, the second stage further refines the first depth map using the confidence maps. The second stage consists of two layers, each of which focuses on different regions and generates a refined depth map and a confidence map. The final depth map is obtained by combining two depth maps from the second stage using the corresponding confidence maps. Compared with the top-ranked models on the KITTI depth completion online leaderboard, the proposed model shows much faster computation time and competitive performance.