Robust ID-Specific Face Restoration via Alignment Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912557437026304 |
|---|---|
| author | Fang, Yushun Liu, Lu Gao, Xiang Hu, Qiang Cao, Ning Cui, Jianghe Chen, Gang Zhang, Xiaoyun |
| author_facet | Fang, Yushun Liu, Lu Gao, Xiang Hu, Qiang Cao, Ning Cui, Jianghe Chen, Gang Zhang, Xiaoyun |
| contents | The latest developments in Face Restoration have yielded significant advancements in visual quality through the utilization of diverse diffusion priors. Nevertheless, the uncertainty of face identity introduced by identity-obscure inputs and stochastic generative processes remains unresolved. To address this challenge, we present Robust ID-Specific Face Restoration (RIDFR), a novel ID-specific face restoration framework based on diffusion models. Specifically, RIDFR leverages a pre-trained diffusion model in conjunction with two parallel conditioning modules. The Content Injection Module inputs the severely degraded image, while the Identity Injection Module integrates the specific identity from a given image. Subsequently, RIDFR incorporates Alignment Learning, which aligns the restoration results from multiple references with the same identity in order to suppress the interference of ID-irrelevant face semantics (e.g. pose, expression, make-up, hair style). Experiments demonstrate that our framework outperforms the state-of-the-art methods, reconstructing high-quality ID-specific results with high identity fidelity and demonstrating strong robustness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_10943 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Robust ID-Specific Face Restoration via Alignment Learning Fang, Yushun Liu, Lu Gao, Xiang Hu, Qiang Cao, Ning Cui, Jianghe Chen, Gang Zhang, Xiaoyun Computer Vision and Pattern Recognition The latest developments in Face Restoration have yielded significant advancements in visual quality through the utilization of diverse diffusion priors. Nevertheless, the uncertainty of face identity introduced by identity-obscure inputs and stochastic generative processes remains unresolved. To address this challenge, we present Robust ID-Specific Face Restoration (RIDFR), a novel ID-specific face restoration framework based on diffusion models. Specifically, RIDFR leverages a pre-trained diffusion model in conjunction with two parallel conditioning modules. The Content Injection Module inputs the severely degraded image, while the Identity Injection Module integrates the specific identity from a given image. Subsequently, RIDFR incorporates Alignment Learning, which aligns the restoration results from multiple references with the same identity in order to suppress the interference of ID-irrelevant face semantics (e.g. pose, expression, make-up, hair style). Experiments demonstrate that our framework outperforms the state-of-the-art methods, reconstructing high-quality ID-specific results with high identity fidelity and demonstrating strong robustness. |
| title | Robust ID-Specific Face Restoration via Alignment Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.10943 |