A new robust estimator based on an evolutionary optimization technique is 
proposed. The general hypothesize-and-verify strategy accelerates the parameter 
estimation substantially by systematic trial and parallel evaluation without the 
use of prior information. The method is evaluated by estimation of multi-view 
relations, i.e. the fundamental matrix. Additionally, some results for the 
trifocal geometry are presented. However, the general methodology could be used 
for any problem in which relations can be determined from a minimum number of 
points.