Self-Supervised Monocular Scene Decomposition and Depth Estimation

10/21/2021
by   Sadra Safadoust, et al.
0

Self-supervised monocular depth estimation approaches either ignore independently moving objects in the scene or need a separate segmentation step to identify them. We propose MonoDepthSeg to jointly estimate depth and segment moving objects from monocular video without using any ground-truth labels. We decompose the scene into a fixed number of components where each component corresponds to a region on the image with its own transformation matrix representing its motion. We estimate both the mask and the motion of each component efficiently with a shared encoder. We evaluate our method on three driving datasets and show that our model clearly improves depth estimation while decomposing the scene into separately moving components.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset