Local stereo matching algorithms based on adapting-weights aggregation produce excellent results compared to other lo- cal methods. In particular, they produce more accurate results near disparity edges. This improvement is obtained thanks to the fact that the support for each pixel is accurately deter- mined based on information such as colour or spatial distance. However, the computation of the support for each pixel results in computationally complex algorithms, especially when us- ing large aggregation windows. Iterative aggregation schemes are a potential alternative to using large windows. In this paper we propose a novel iterative approach for adapting- weights aggregation which produces better results and out- performs most previous adapting-weights methods.
L. De-Maeztu, S. Mattoccia, A. Villanueva, R. Cabeza (2011). EFFICIENT AGGREGATION VIA ITERATIVE BLOCK-BASED ADAPTING SUPPORT-WEIGHTS. LIÈGE : IEEE [10.1109/IC3D.2011.6584379].
EFFICIENT AGGREGATION VIA ITERATIVE BLOCK-BASED ADAPTING SUPPORT-WEIGHTS
MATTOCCIA, STEFANO;
2011
Abstract
Local stereo matching algorithms based on adapting-weights aggregation produce excellent results compared to other lo- cal methods. In particular, they produce more accurate results near disparity edges. This improvement is obtained thanks to the fact that the support for each pixel is accurately deter- mined based on information such as colour or spatial distance. However, the computation of the support for each pixel results in computationally complex algorithms, especially when us- ing large aggregation windows. Iterative aggregation schemes are a potential alternative to using large windows. In this paper we propose a novel iterative approach for adapting- weights aggregation which produces better results and out- performs most previous adapting-weights methods.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
