In this work we present a Bayesian interpolation procedure to perform depth map upsampling. The depth map prior is designed via an edge driven Markov Random Field. The upsampling procedure is computationally efficient and outperforms selected state of the art upsampling procedure; moreover it allows to perform depth map upsampling even without the reference high resolution luminance map. © 2012 Taylor & Francis Group.
Bayesian depth map interpolation using edge driven Markov Random Fields / Colonnese, Stefania; Rinauro, Stefano; Scarano, Gaetano. - STAMPA. - (2012), pp. 143-146. (Intervento presentato al convegno 3rd International Symposium on Computational Modelling of Objects Represented in Images: Fundamentals, Methods and Applications, CompIMAGE 2012 tenutosi a Rome nel 5 September 2012 through 7 September 2012) [10.1201/b12753-26].
Bayesian depth map interpolation using edge driven Markov Random Fields
COLONNESE, Stefania;RINAURO, STEFANO;SCARANO, Gaetano
2012
Abstract
In this work we present a Bayesian interpolation procedure to perform depth map upsampling. The depth map prior is designed via an edge driven Markov Random Field. The upsampling procedure is computationally efficient and outperforms selected state of the art upsampling procedure; moreover it allows to perform depth map upsampling even without the reference high resolution luminance map. © 2012 Taylor & Francis Group.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
