AlignCVC: Aligning Cross-View Consistency for Single-Image-to-3D Generation
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (9) · 6889-6897
DOI: 10.1609/aaai.v40i9.37622 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xinyue Liang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
Single-image-to-3D models typically follow a sequential generation and reconstruction workflow. However, intermediate multi-view images synthesized by pre-trained generation models often lack cross-view consistency (CVC), significantly degrading 3D reconstruction performance. While recent methods attempt to refine CVC by feeding reconstruction results back into the multi-view generator, these approaches struggle with noisy and unstable reconstruction outputs that limit effective CVC improvement. We introduce AlignCVC, a novel framework that fundamentally re-frames single-image-to-3D generation through distribution alignment rather than relying on strict regression losses. Our key insight is to align both generated and reconstructed multi-view distributions toward the ground-truth multi-view distribution, establishing a principled foundation for improved CVC. Observing that generated images exhibit weak CVC while reconstructed images display strong CVC due to explicit rendering, we propose a soft-hard alignment strategy with distinct objectives for generation and reconstruction models. This approach not only enhances generation quality but also dramatically accelerates inference to as few as 4 steps. As a plug-and-play paradigm, our method, namely AlignCVC, seamlessly integrates various combinations of multiview generation models with 3D reconstruction models. Extensive experiments demonstrate the effectiveness and efficiency of AlignCVC for single-image-to-3D generation.
Zitieren
APA
Liang, X., Ma, Z., Sun, L., Guo, Y., & Zhang, L. (2026). AlignCVC: Aligning Cross-View Consistency for Single-Image-to-3D Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(9), 6889-6897. https://doi.org/10.1609/aaai.v40i9.37622
Vancouver
Liang X, Ma Z, Sun L, Guo Y, Zhang L. AlignCVC: Aligning Cross-View Consistency for Single-Image-to-3D Generation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(9):6889-6897. doi:10.1609/aaai.v40i9.37622
BibTeX
@article{Liang2026,
author = {Liang, Xinyue and Ma, Zhiyuan and Sun, Lingchen and Guo, Yanjun and Zhang, Lei},
title = {AlignCVC: Aligning Cross-View Consistency for Single-Image-to-3D Generation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {9},
pages = {6889--6897},
doi = {10.1609/aaai.v40i9.37622}
}
EUVIMED