MonoComb: A Sparse-to-Dense Combination Approach for Monocular Scene Flow
It addresses scene flow estimation for automotive applications with only one sensor, which is incremental over existing methods.
The paper tackles the monocular scene flow problem using a single camera by combining single image depth estimation, optical flow, and sparse-to-dense interpolation, achieving the second-best result on the KITTI 2015 benchmark.
Contrary to the ongoing trend in automotive applications towards usage of more diverse and more sensors, this work tries to solve the complex scene flow problem under a monocular camera setup, i.e. using a single sensor. Towards this end, we exploit the latest achievements in single image depth estimation, optical flow, and sparse-to-dense interpolation and propose a monocular combination approach (MonoComb) to compute dense scene flow. MonoComb uses optical flow to relate reconstructed 3D positions over time and interpolates occluded areas. This way, existing monocular methods are outperformed in dynamic foreground regions which leads to the second best result among the competitors on the challenging KITTI 2015 scene flow benchmark.