MV-S2V: Multi-View Subject-Consistent Video Generation
It addresses a limitation in subject-driven video generation for AI and creative applications, introducing a new task direction but with incremental technical improvements.
The paper tackles the problem of generating videos from multiple reference views to ensure 3D-level subject consistency, proposing MV-S2V with a synthetic data pipeline and TS-RoPE method, achieving superior 3D subject consistency and high-quality outputs.
Existing Subject-to-Video Generation (S2V) methods have achieved high-fidelity and subject-consistent video generation, yet remain constrained to single-view subject references. This limitation renders the S2V task reducible to an S2I + I2V pipeline, failing to exploit the full potential of video subject control. In this work, we propose and address the challenging Multi-View S2V (MV-S2V) task, which synthesizes videos from multiple reference views to enforce 3D-level subject consistency. Regarding the scarcity of training data, we first develop a synthetic data curation pipeline to generate highly customized synthetic data, complemented by a small-scale real-world captured dataset to boost the training of MV-S2V. Another key issue lies in the potential confusion between cross-subject and cross-view references in conditional generation. To overcome this, we further introduce Temporally Shifted RoPE (TS-RoPE) to distinguish between different subjects and distinct views of the same subject in reference conditioning. Our framework achieves superior 3D subject consistency w.r.t. multi-view reference images and high-quality visual outputs, establishing a new meaningful direction for subject-driven video generation. Our project page is available at <a href="https://szy-young.github.io/mv-s2v">this URL</a>