Abstract
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.
Recommended Citation
T. Wang et al., "You Only Need One Stage: Novel-View Synthesis from a Single Blind Face Image," Proceedings of the Aaai Conference on Artificial Intelligence, vol. 40, no. 12, pp. 10127 - 10135, Association for the Advancement of Artificial Intelligence, Jan 2026.
The definitive version is available at https://doi.org/10.1609/aaai.v40i12.37980
Department(s)
Computer Science
International Standard Serial Number (ISSN)
2374-3468; 2159-5399
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2026 Association for the Advancement of Artificial Intelligence, All rights reserved.
Publication Date
01 Jan 2026
Comments
Office of the Director of National Intelligence, Grant 2022-21102100003