Abstract Despite the success of current state-of-the-art object class detectors, severe occlusion remains a major challenge. This is particularly true for more geometrically expressive 3D object class representations. While these representations have attracted renewed interest for precise object pose estimation, the focus has mostly been on rather clean datasets, where occlusion is not an issue. In this paper, we tackle the challenge of modeling occlusion in the context of a 3D geometric object class model that is capable of ?ne-grained, part-level 3D object reconstruction. Following the intuition that 3D modeling should facilitate occlusion reasoning, we design an explicit representation of likely geometric occlusion patterns. Robustness is achieved by pooling image evidence from of a set of ?xed part detectors as well as a non-parametric representation of part con?gurations in the spirit of poselets. We con?rm the potential of our method on cars in a newly collected data set inner-city street scenes with varying levels of occlusion, a demonstrate superior performance in occlusion estimation and part localization, compared to baselines that are unaware of occlusions.