StereoPilot: Learning Unified and Efficient Stereo Conversion via Generative Priors
This work addresses the costly and complex production of 3D videos for stereoscopic displays like VR headsets and 3D cinemas, representing a strong specific gain in the domain.
The paper tackles the problem of high-quality stereo video conversion from monocular inputs by addressing limitations in existing multi-stage pipelines, and introduces StereoPilot, an efficient feed-forward model that outperforms state-of-the-art methods in visual fidelity and computational efficiency.
The rapid growth of stereoscopic displays, including VR headsets and 3D cinemas, has led to increasing demand for high-quality stereo video content. However, producing 3D videos remains costly and complex, while automatic Monocular-to-Stereo conversion is hindered by the limitations of the multi-stage ``Depth-Warp-Inpaint'' (DWI) pipeline. This paradigm suffers from error propagation, depth ambiguity, and format inconsistency between parallel and converged stereo configurations. To address these challenges, we introduce UniStereo, the first large-scale unified dataset for stereo video conversion, covering both stereo formats to enable fair benchmarking and robust model training. Building upon this dataset, we propose StereoPilot, an efficient feed-forward model that directly synthesizes the target view without relying on explicit depth maps or iterative diffusion sampling. Equipped with a learnable domain switcher and a cycle consistency loss, StereoPilot adapts seamlessly to different stereo formats and achieves improved consistency. Extensive experiments demonstrate that StereoPilot significantly outperforms state-of-the-art methods in both visual fidelity and computational efficiency. Project page: https://hit-perfect.github.io/StereoPilot/.