diff --git a/registration/include/pcl/registration/gicp.h b/registration/include/pcl/registration/gicp.h
index a7afb898409..4e565117264 100644
--- a/registration/include/pcl/registration/gicp.h
+++ b/registration/include/pcl/registration/gicp.h
@@ -48,7 +48,7 @@ namespace pcl
 {
   /** \brief GeneralizedIterativeClosestPoint is an ICP variant that implements the 
     * generalized iterative closest point algorithm as described by Alex Segal et al. in 
-    * http://www.stanford.edu/~avsegal/resources/papers/Generalized_ICP.pdf
+    * http://www.robots.ox.ac.uk/~avsegal/resources/papers/Generalized_ICP.pdf
     * The approach is based on using anistropic cost functions to optimize the alignment 
     * after closest point assignments have been made.
     * The original code uses GSL and ANN while in ours we use an eigen mapped BFGS and 
diff --git a/registration/include/pcl/registration/impl/gicp.hpp b/registration/include/pcl/registration/impl/gicp.hpp
index ab9ba8dea30..c430b0f13ba 100644
--- a/registration/include/pcl/registration/impl/gicp.hpp
+++ b/registration/include/pcl/registration/impl/gicp.hpp
@@ -466,6 +466,9 @@ pcl::GeneralizedIterativeClosestPoint<PointSource, PointTarget>::computeTransfor
   final_transformation_(0,3) = previous_transformation_(0,3) + guess(0,3);
   final_transformation_(1,3) = previous_transformation_(1,3) + guess(1,3);
   final_transformation_(2,3) = previous_transformation_(2,3) + guess(2,3);
+
+  // Transform the point cloud
+  pcl::transformPointCloud (*input_, output, final_transformation_);
 }
 
 template <typename PointSource, typename PointTarget> void