Disambiguating Monocular Depth Estimation with a Single Transient (ECCV 2020)

Monocular depth estimation algorithms successfully predict the relative depth order of objects in a scene. However, because of the fundamental scale ambiguity associated with monocular images, these algorithms fail at correctly predicting true metric depth. In this work, we demonstrate how a depth histogram of the scene, which can be readily captured using a single-pixel time-resolved detector, can be fused with the output of existing monocular depth estimation algorithms to resolve the depth ambiguity problem. We validate this novel sensor fusion technique experimentally and in extensive simulation. We show that it significantly improves the performance of several state-of-the-art monocular depth estimation algorithms.

Видео Disambiguating Monocular Depth Estimation with a Single Transient (ECCV 2020) канала Stanford Computational Imaging Lab