This Ph.D. thesis deals with the improvement of video compression efficiency. Both conventional and breakthrough approaches are investigated in order to propose efficient methods for Intra and Inter coding dedicated to next generations video coding standards. Two tools are studied for the conventional approach. First, syntax elements are cleverly trans- mitted using a data hiding based method which allows embedding indices into the luminance and chrominance residuals in an optimal way, rate-distortion wise. Secondly, the large motion redundancies are exploited to improve the motion vectors coding. After a statistical analysis of the previously used vectors, an accurate forecast is performed to favour some vector residuals during a last step which modifies the original residual distribution. 90% of the coded vectors are efficiently forecasted by this method which helps to significantly reduce their coding cost. The breakthrough approach comes from the observation of the H.264/AVC standard and its successor HEVC which are based on a predictive scheme with multiple coding choices, conse- quently future improvements shall improve texture by extensively using the competition between many coding modes. However, such schemes are bounded by the cost generated by the signalling flags and therefore it is required to transfer some decisions to the decoder side. A framework based on the determination of encoding parameters at both encoder and decoder side is consequently proposed and applied to Intra prediction modes on the one hand, and to the emerging theory of compressed sensing on the other hand. Promising results are reported and confirm the potential of such an innovative solution.