Monocular Depth Estimation

Monocular depth estimation is the task of estimating the depth value of each pixel relative to the camera given a single RGB image. This task is a key prerequisite for scene understanding in applications such as 3D scene reconstruction, autonomous driving, and augmented reality. Current mainstream methods include designing complex networks to directly regress depth maps, or segmenting the input into multiple intervals to reduce computational complexity. Common evaluation metrics include Root Mean Square Error (RMSE) and Absolute Relative Error.