The paper describes a method for depth extraction from multiple, calibrated images. Emphasis lies on the integration of multiple views during the matching process. This process is guided by the relative confidence that the system has in the data coming from the different views. This weighing is fine-grained in that it is determined for every pixel at every iteration. Reliable information spreads fast at the expense of less reliable data, both in terms of spatial communications and in terms of exchange between views. The resulting system can handle large disparities, depth discontinuities and occlusions. Moreover, provisions are made to deal with intensity changes between corresponding pixels. Experimental results corroborate the viability of the approach and the improved results that can be expected from the system?s ability to deal with variable intensities.