Introduction to Coherent Depth Fields for Dense Monocular Surface Recovery

Introduction to Coherent Depth Fields for Dense Monocular Surface Recovery
Vladislav Golyanik, Torben Fetzer, Didier Stricker
Proceedings of the British Machine Vision Conference British Machine Vision Conference (BMVC-17), London, United Kingdom

Handling large occlusions in non-rigid structure from motion (NRSfM) currently requires either an expensive correspondence correction or estimation of a shape prior on several non-occluded views. To save computational cost and remove the dependency on additional pre-processing steps, this paper introduces the concept of depth fields. With the proposed depth fields, NRSfM is interpreted as an alternating estimation of vector fields with fixed origins on the one side, and estimation of displacements of the origins along the depth dimension on the other. The core of the new energy-based Coherent Depth Fields (CDF) approach is the spatial smoothness coherency term (CT) applied on the depth fields. Having its origins in the Motion Coherence Theory, CT interprets data as a displacement vector field and penalises irregularities in displacements. Not only for handling occlusions but also for unoccluded scenes CT has multiple advantages compared to previously proposed regularisers such as total variation. We show experimentally that CDF achieves state-of-the-art in dense NRSfM including scenarios with long and large occlusions, inaccurate correspondences as well as inaccurate initialisations, without requiring any additional pre-processing steps.
Motion Coherence Theory, Coherent Depth Fields, Coherency Term, Non-Rigid Structure From Motion, Occlusion Handling