INTERLCM: low-quality images as intermediate states of latent consistency models for effective blind face restoration
Li, Senmao Wang, Kai van de Weijer, Joost Khan, Fahad Guo, Chun-Le Yang, Shiqi Wang, Yaxing Yang, Jian Cheng, Ming-Ming
Li, Senmao
Wang, Kai
van de Weijer, Joost
Khan, Fahad
Guo, Chun-Le
Yang, Shiqi
Wang, Yaxing
Yang, Jian
Cheng, Ming-Ming
Supervisor
Department
Computer Vision
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Diffusion priors have been used for blind face restoration (BFR) by fine-tuning diffusion models (DMs) on restoration datasets to recover low-quality images. However, the naive application of DMs presents several key limitations. (i) The diffusion prior has inferior semantic consistency (e.g., ID, structure and color.), increasing the difficulty of optimizing the BFR model; (ii) reliance on hundreds of denoising iterations, preventing the effective cooperation with perceptual losses, which is crucial for faithful restoration. Observing that the latent consistency model (LCM) learns consistency noise-to-data mappings on the ODE-trajectory and therefore shows more semantic consistency in the subject identity, structural information and color preservation, we propose InterLCM to leverage the LCM for its superior semantic consistency and efficiency to counter the above issues. Treating low-quality images as the intermediate state of LCM, InterLCM achieves a balance between fidelity and quality by starting from earlier LCM steps. LCM also allows the integration of perceptual loss during training, leading to improved restoration quality, particularly in real-world scenarios. To mitigate structural and semantic uncertainties, InterLCM incorporates a Visual Module to extract visual features and a Spatial Encoder to capture spatial details, enhancing the fidelity of restored images. Extensive experiments demonstrate that InterLCM outperforms existing approaches in both synthetic and real-world datasets while also achieving faster inference speed. Project page: https://sen-mao.github.io/InterLCM-Page/. © 2025 13th International Conference on Learning Representations, ICLR 2025. All rights reserved.
Citation
S. Li et al., “InterLCM: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restoration,” International Conference on Representation Learning, vol. 2025, pp. 59165–59197, May 2025, Accessed: Jul. 23, 2025
Source
13th International Conference on Learning Representations, ICLR 2025
Conference
13th International Conference on Learning Representations, ICLR 2025
Keywords
Subjects
Source
13th International Conference on Learning Representations, ICLR 2025
Publisher
International Conference on Learning Representations, ICLR