Temporally consistent dense depth map estimation via Belief Propagation

Abstract

A method for estimating temporally and spatially consistent dense depth maps in multiple camera setups is presented which is important for reduction of perception artifacts in 3D displays. For this purpose, initially, depth estimation is performed for each camera with the piece-wise planarity assumption and Markov Random Field (MRF) based relaxation at each time instant independently. During the relaxation step, the consistency of depth maps for different cameras is also considered for the reliability of the models. Next, temporal consistency of the depth maps is achieved in two steps. In the first step, median filtering is applied for the static or background pixels, whose intensity levels are constant in time. Such an approach decreases the number of inconsistent depth values significantly. The second step considers the moving pixels and MRF formulation is updated by the additional information from the depth maps of the consequent frames through motion compensation. For the solution of the MRF formulation for both spatial and temporal consistency, Belief Propagation approach is utilized. The experiments indicate that the proposed method provide reliable dense depth map estimates both in spatial and temporal domains.