In this paper, we propose a new Distributed Video Coding (DVC) architecture where motion estimation is performed both at the encoder and decoder, effectively combining global and local motion models. We show that the proposed approach improves significantly the quality of Side Information (SI), especially for sequences with complex motion patterns. In turn, it leads to rate-distortion gains of up to 1 dB when compared to the state-of-the-art DISCOVER DVC codec.