Methods and apparatus for hidden surface removal with soft occlusion. Soft occlusion methods are described that treat surfaces as having a degree of uncertainty in depth. The soft occlusion methods may, for example, be used to remove artifacts from rendered images due to nearly coplanar surfaces or to render novel effects such as soft intersections between objects including consistent shadows and other global illumination effects. The soft occlusion methods may compute the ‘expected’ or average image given depth probability density functions. This has the effect of visually blending together surfaces that are close together in depth, leading to soft intersections. The computation of soft occlusion may be achieved analytically, for certain probability density functions, or stochastically. The stochastic soft occlusion methods extend the approach to a probability distribution of models, which allows for the effects of shadows and other global illumination effects to be included.