In this work we propose, for the rst time, to improve the performance of a hand pose reconstruction (HPR) technique from RGBD camera data, which is aected by self-occlusions, leveraging upon postural synergy information, i.e., a priori information on how human most commonly use and shape their hands in everyday life tasks. More specifically, in our approach, we ignore joint angle values estimated with low condence through a vision-based HPR technique and fuse synergistic information with such incomplete measures. Preliminary experiments are reported showing the eectiveness of the proposed integration.