Purpose: Single Incision Laparoscopic Surgery (SILS) decreases post-operative infections, but introduces limitations in the surgeon's manoeuverability and in the surgical field of view. This work aims at enhancing intraoperative surgical visualization by exploiting the 3D information about the surgical site. An interactive guidance system is proposed wherein the pose of pre-operative tissue models is updated online. A critical process involves the intraoperative acquisition of tissue surfaces. It can be achieved using stereoscopic imaging and 3D reconstruction techniques. This work contributes to this process by proposing new methods for improved dense 3D reconstruction of soft tissues, which allows a more accurate deformation identification and facilitates the registration process.Methods: Two methods for soft tissue 3D reconstruction are proposed: Method 1 follows the traditional approach of the block matching algorithm. Method 2 performs a non-parametric Modified Census Transform to be more robust to illumination variation. The Simple Linear Iterative Clustering (SLIC) super pixel al- gorithm is exploited for disparity refinement by filling holes in the disparity images.Results: The methods were validated using two video datasets from the Hamlyn Centre, achieving an accuracy of 2.95 mm and 1.66 mm respectively. A comparison with ground truth data demonstrated the disparity refinement procedure: (i) increases the number of reconstructed points by up to 43%; (ii) does not a↵ect the accuracy of the 3D reconstructions significantly.Conclusion: Both methods give results that compare favourably with the state-of-the-art methods. The computational time constraints their applicability in realtime, but can be greatly improved by using a GPU implementation.