EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DissolveStereo: Coarse Depth Injection for Zero-Shot Stereo Video Generation

Jian Shi, Qian Wang, Zhenyu Li, Wenqing Cui, Ramzi Idoughi, Peter Wonka

ACM Transactions on Graphics · 03.07.2026 · 45 (4) · 1-14

DOI: 10.1145/3811390 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 03.07.2026. Verfasst von Jian Shi und 5 weiteren Autor:innen. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Generating high-quality stereo videos requires consistent depth perception and temporal coherence across frames. Despite advances in image and video synthesis using diffusion models, producing high-quality stereo videos remains a challenging task due to the difficulty of maintaining consistent temporal and spatial coherence between left and right views. We introduce DissolveStereo , a novel framework for zero-shot stereo video generation that leverages video diffusion priors without requiring paired training data. Our key innovations include a noisy restart strategy to initialize stereo-aware latent representations and an iterative refinement process that progressively harmonizes the latent space, addressing issues like temporal flickering and view inconsistencies. Importantly, we propose the use of dissolved depth maps to streamline latent space operations by reducing high-frequency depth information. Our comprehensive evaluations, including quantitative metrics and user studies, demonstrate that DissolveStereo produces high-quality stereo videos with enhanced depth consistency and temporal smoothness. In terms of epipolar consistency, our method achieves an 11.7% improvement in MEt3R score over the current state-of-the-art. Furthermore, user studies indicate strong perceptual gains over the previous arts, with an 8.0% higher perceived frame quality and 10.9% higher perceived temporal coherence. Our code is in https://github.com/shijianjian/DissolveStereo.

Zitieren

APA

Shi, J., Wang, Q., Li, Z., Cui, W., Idoughi, R., & Wonka, P. (2026). DissolveStereo: Coarse Depth Injection for Zero-Shot Stereo Video Generation. ACM Transactions on Graphics, 45(4), 1-14. https://doi.org/10.1145/3811390

Vancouver

Shi J, Wang Q, Li Z, Cui W, Idoughi R, Wonka P. DissolveStereo: Coarse Depth Injection for Zero-Shot Stereo Video Generation. ACM Transactions on Graphics. 2026;45(4):1-14. doi:10.1145/3811390

BibTeX
@article{Shi2026,
  author = {Shi, Jian and Wang, Qian and Li, Zhenyu and Cui, Wenqing and Idoughi, Ramzi and Wonka, Peter},
  title = {DissolveStereo: Coarse Depth Injection for Zero-Shot Stereo Video Generation},
  journal = {ACM Transactions on Graphics},
  year = {2026},
  volume = {45},
  number = {4},
  pages = {1--14},
  doi = {10.1145/3811390}
}
Kostenlos starten →