You Only Need One Stage: Novel-View Synthesis from a Single Blind Face Image
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (12) · 10127-10135
DOI: 10.1609/aaai.v40i12.37980 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Taoyue Wang und 4 weiteren Autor:innen.
Abstract (Originalsprache)
We propose a novel one-stage method, NVB-Face, for generating consistent Novel-View images directly from a single Blind Face image. Existing approaches to novel-view synthesis for objects or faces typically require a high-resolution RGB image as input. When dealing with degraded images, the conventional pipeline follows a two-stage process: first restoring the image to high resolution, then synthesizing novel views from the restored result. However, this approach is highly dependent on the quality of the restored image, often leading to inaccuracies and inconsistencies in the final output. To address this limitation, we extract single-view features directly from the blind face image and introduce a feature manipulator that transforms these features into 3D-aware, multi-view latent representations. Leveraging the powerful generative capacity of a diffusion model, our framework synthesizes high-quality, consistent novel-view face images. Experimental results show that our method significantly outperforms traditional two-stage approaches in both consistency and fidelity.
Zitieren
APA
Wang, T., Zhang, X., Li, X., Yang, H., & Yin, L. (2026). You Only Need One Stage: Novel-View Synthesis from a Single Blind Face Image. Proceedings of the AAAI Conference on Artificial Intelligence, 40(12), 10127-10135. https://doi.org/10.1609/aaai.v40i12.37980
Vancouver
Wang T, Zhang X, Li X, Yang H, Yin L. You Only Need One Stage: Novel-View Synthesis from a Single Blind Face Image. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(12):10127-10135. doi:10.1609/aaai.v40i12.37980
BibTeX
@article{Wang2026,
author = {Wang, Taoyue and Zhang, Xiang and Li, Xiaotian and Yang, Huiyuan and Yin, Lijun},
title = {You Only Need One Stage: Novel-View Synthesis from a Single Blind Face Image},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {12},
pages = {10127--10135},
doi = {10.1609/aaai.v40i12.37980}
}
EUVIMED