StereoPilot: Learning Unified and Efficient Stereo Conversion via Generative Priors

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Shen, Guibao, Du, Yihua, Ge, Wenhang, He, Jing, Chang, Chirui, Zhou, Donghao, Yang, Zhen, Wang, Luozhou, Tao, Xin, Chen, Ying-Cong
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918255494430720
author Shen, Guibao
Du, Yihua
Ge, Wenhang
He, Jing
Chang, Chirui
Zhou, Donghao
Yang, Zhen
Wang, Luozhou
Tao, Xin
Chen, Ying-Cong
author_facet Shen, Guibao
Du, Yihua
Ge, Wenhang
He, Jing
Chang, Chirui
Zhou, Donghao
Yang, Zhen
Wang, Luozhou
Tao, Xin
Chen, Ying-Cong
contents 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/.
format Preprint
id arxiv_https___arxiv_org_abs_2512_16915
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle StereoPilot: Learning Unified and Efficient Stereo Conversion via Generative Priors
Shen, Guibao
Du, Yihua
Ge, Wenhang
He, Jing
Chang, Chirui
Zhou, Donghao
Yang, Zhen
Wang, Luozhou
Tao, Xin
Chen, Ying-Cong
Computer Vision and Pattern Recognition
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/.
title StereoPilot: Learning Unified and Efficient Stereo Conversion via Generative Priors
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.16915