Temporally Coherent Disparity Maps Using CRFs with Fast 4D Filtering (conference version)
Siavash Arjomand Bigdeli, Gregor Budweiser, Matthias Zwicker
Asian Conference on Pattern Recognition (ACPR), 2015, oral presentation paper,
supplementary material
Abstract
State of the art
methods for disparity estimation achieve good
results for single stereo frames, but temporal
coherence in stereo videos is often neglected. In
this paper we present a method to compute temporally
coherent disparity maps. We define an energy over
whole stereo sequences and optimize their
Conditional Random Field (CRF) distributions using
mean-field approximation. We introduce novel terms
for smoothness and consistency between the left and
right views, and perform CRF optimization by fast,
iterative spatio-temporal filtering with linear
complexity in the total number of pixels. Our
results rank among the state of the art while having
significantly less flickering artifacts in stereo
sequences.
paper
supplementary material