One-Shot Refiner: Boosting Feed-forward Novel View Synthesis via One-Step Diffusion
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (5) · 3659-3667
DOI: 10.1609/aaai.v40i5.37365 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yitong Dong und 8 weiteren Autor:innen.
Abstract (Originalsprache)
We present a novel framework for high-fidelity novel view synthesis (NVS) from sparse images, addressing key limitations in recent feed-forward 3D Gaussian Splatting (3DGS) methods built on Vision Transformer (ViT) backbones. While ViT-based pipelines offer strong geometric priors, they are often constrained by low-resolution inputs due to computational costs. Moreover, existing generative enhancement methods tend to be 3D-agnostic, resulting in inconsistent structures across views, especially in unseen regions. To overcome these challenges, we design a Dual-Domain Detail Perception Module, which enables handling high-resolution images without being limited by the ViT backbone, and endows Gaussians with additional features to store high-frequency details. We develop a feature-guided diffusion network, which can preserve high-frequency details during the restoration process. We introduce a unified training strategy that enables joint optimization of the ViT-based geometric backbone and the diffusion-based refinement module. Experiments demonstrate that our method can maintain superior generation quality across multiple datasets.
Zitieren
APA
Dong, Y., Zhang, Q., Jiang, M., Wu, Z., Fan, Q., Feng, Y., Zhang, H., Bao, H., & Zhang, G. (2026). One-Shot Refiner: Boosting Feed-forward Novel View Synthesis via One-Step Diffusion. Proceedings of the AAAI Conference on Artificial Intelligence, 40(5), 3659-3667. https://doi.org/10.1609/aaai.v40i5.37365
Vancouver
Dong Y, Zhang Q, Jiang M, Wu Z, Fan Q, Feng Y, et al. One-Shot Refiner: Boosting Feed-forward Novel View Synthesis via One-Step Diffusion. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(5):3659-3667. doi:10.1609/aaai.v40i5.37365
BibTeX
@article{Dong2026,
author = {Dong, Yitong and Zhang, Qi and Jiang, Minchao and Wu, Zhiqiang and Fan, Qingnan and Feng, Ying and Zhang, Huaqi and Bao, Hujun and Zhang, Guofeng},
title = {One-Shot Refiner: Boosting Feed-forward Novel View Synthesis via One-Step Diffusion},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {5},
pages = {3659--3667},
doi = {10.1609/aaai.v40i5.37365}
}
EUVIMED