MonoComb: A Sparse-to-Dense Combination Approach for Monocular Scene Flow

Contrary to the ongoing trend in automotive applications towards usage of\nmore diverse and more sensors, this work tries to solve the complex scene flow\nproblem under a monocular camera setup, i.e. using a single sensor. Towards\nthis end, we exploit the latest achievements in single image depth estimation,\noptical flow, and sparse-to-dense interpolation and propose a monocular\ncombination approach (MonoComb) to compute dense scene flow. MonoComb uses\noptical flow to relate reconstructed 3D positions over time and interpolates\noccluded areas. This way, existing monocular methods are outperformed in\ndynamic foreground regions which leads to the second best result among the\ncompetitors on the challenging KITTI 2015 scene flow benchmark.\n