Depth Completion

Depth completion is a sub-problem of depth estimation in computer vision. Its goal is to infer a dense depth map of a 3D scene given an RGB image and its corresponding sparse depth map. Sparse depth maps are typically obtained through active sensors such as structured light or LiDAR, or computational methods like Structure from Motion (SfM). Depth completion techniques are of significant value in fields such as autonomous driving, robot navigation, and augmented reality.