- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper introduces RefRouteFR, a one-step multi-reference face restoration method based on FLUX2. The main idea is to use a lightweight router in the Transformer’s single-stream blocks to select the Top-K important tokens from multiple reference images, reducing redundant computation while using a latent calibrator to improve restoration quality. Experiments show that this method can significantly cut down FLOPs and inference time while maintaining good restoration and identity consistency. The paper also includes ablation studies on token numbers, the number of references, and router design. ...
— —We have re-examined the paper and reconsidered our assessment in light of the authors’ responses and the other reviewers’ comments. The clarifications regarding the source of test prompts, the FFHQ-Ref evaluation protocol, and reference selection, together with the additional baseline comparisons, address our main concerns. Although the real-world evaluation remains limited in scale, we are inclined to raise our rating from 2 (Weak rejection) to 3 (Weak acceptance).
Critical strengths
- Effective computational efficiency optimization. Reference-token routing can significantly reduce computation while avoiding the introduction of an extra complex reference network, which is practically meaningful for multi-reference image scenarios.
- Ablation experiments are quite thorough. The authors systematically analyzed token budget, the number of reference images, and router design, providing some support for the method's effectiveness.
Critical weaknesses
- Experimental protocol is not clear enough and baselines are incomplete. The specific settings for FFHQ-Ref, the number of reference images, and the comparison conditions for different baselines are not sufficiently explained. Additionally, several recent directly related methods are missing for comparison.
- There are potential issues with prompt setup. During training, prompts generated from GT images are used, but the paper does not clearly specify what prompts are used during testing. If GT-derived prompts are also used during testing, there might be target information leakage; if generic prompts are used, there is an obvious train-test mismatch. Moreover, the real-world experiment scale is relatively small.
Questions for authors
- What prompts are specifically used during testing? Can you confirm that GT image information is completely excluded during testing?
- Please clarify which standard setting is used for FFHQ-Ref and how many reference images are used for each baseline.
- Could you include recent directly related methods and compare them under fully consistent reference/evaluation protocols?
3 comments
Response to W1/Q3 and W2: Additional baselines and real-world evaluation
W1 / Q3: Recent related baselines
Response. We additionally evaluate ASFFNet [2] and ReFine [3] on CelebRef-HQ and FFHQ-Ref using their official implementations and released weights, following the evaluation protocol described in W1/Q2. Together with the existing baselines, these comparisons cover both representative earlier methods and recent advances in face restoration, as summarized in Table 2.
Table 2. Publication venues and years of representative baselines.
| Method | ASFFNet | CodeFormer | DMDNet | ReF-LDM | RestorerID |
|---|---|---|---|---|---|
| Publication | CVPR'20 | NeurIPS'22 | TPAMI'23 | NeurIPS'24 | Preprint'24 |
| Method | ReFine | InstantRestore | FaceMe | RefSTAR | AdaRefSR |
| Publication | WACV'25 | SIGGRAPH'25 | AAAI'25 | AAAI'26 | ICLR'26 |
As shown in Table 3, both RefRouteFR and RefRouteFR-Full achieve better perceptual quality and identity consistency than these additional baselines on both benchmarks.
Table 3. Additional comparisons on CelebRef-HQ and FFHQ-Ref. Best and second-best results are highlighted in bold and underlined, respectively. Methods marked with * accept multiple reference candidates.
| Method | PSNR↑ | SSIM↑ | LPIPS↓ | FID↓ | IDS↑ | NIQE↓ | MUSIQ↑ | CLIP-IQA↑ |
|---|---|---|---|---|---|---|---|---|
| CelebRef-HQ | ||||||||
| ASFFNet* | 26.4240 | 0.7451 | 0.2178 | 50.5072 | 0.8039 | 4.4892 | 72.0388 | 0.6162 |
| ReFine | 26.8013 | 0.7466 | 0.2157 | 47.5741 | 0.7975 | 4.1885 | 72.6217 | 0.6003 |
| RefRouteFR* | 27.2383 | |||||||
| RefRouteFR-Full* | 0.7516 | 0.1486 | 35.5258 | 0.9021 | 4.0751 | 74.5981 | 0.6236 | |
| FFHQ-Ref | ||||||||
| ASFFNet* | 25.8009 | 0.7144 | 0.2840 | 39.5441 | 0.8039 | 4.4177 | 71.1503 | 0.6108 |
| ReFine | 25.6080 | 0.7178 | 0.3723 | 49.4923 | 0.7602 | 5.9953 | 52.9358 | 0.4713 |
| RefRouteFR* | ||||||||
| RefRouteFR-Full* | 26.6322 | 0.7291 | 0.1699 | 23.9486 | 0.9258 | 3.9052 | 74.1158 | 0.6360 |
Revision. The ASFFNet and ReFine comparisons have been incorporated into Section 4.2 and Table 1.
W2: Real-world evaluation scale
Response. We acknowledge the limited scale of our real-world evaluation, which includes 50 naturally degraded LFW [4] images from 10 identities. Same-identity HQ references are collected from the web, with one or four references provided to single- and multi-reference methods, respectively. Large-scale public benchmarks for real-world reference-based face restoration remain limited, and existing studies often rely on relatively small, privately collected evaluation sets, such as the 60 real-world image pairs used in RefSTAR. We are currently collecting additional real-world samples and corresponding references to expand the scale and diversity of our evaluation.
Revision. Section 4.1 now specifies the scale and composition of the real-world evaluation set.
References
[2] Xiaoming Li, Wenyu Li, Dongwei Ren, Hongzhi Zhang, Meng Wang, and Wangmeng Zuo. Enhanced blind face restoration with multi-exemplar images and adaptive spatial feature fusion. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2706–2715, 2020.
[3] Min Jin Chong, Dejia Xu, Yi Zhang, Zhangyang Wang, David Forsyth, Gurunandan Krishnan, Yicheng Wu, and Jian Wang. Copy or not? reference-based face image restoration with fine details. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2025.
[4] Gary B. Huang, Manu Ramesh, Tamara Berg, and Erik Learned-Miller. Labeled Faces in the Wild: A database for studying face recognition in unconstrained environments. Technical Report 07-49, University of Massachusetts, Amherst, October 2007.
We sincerely thank the reviewer for carefully reconsidering our work and for the constructive feedback. We are glad that our clarifications and additional comparisons have addressed your main concerns. We greatly appreciate your time and thoughtful assessment.
Response to W2/Q1 and W1/Q2: Test-Time Prompts and FFHQ-Ref Protocol
Thank you for recognizing the computational efficiency and the ablation studies. We clarify the information available at test time, the FFHQ-Ref evaluation protocol, and reference counts for each class of method. We also provide additional ASFFNet and ReFine comparisons and describe the scope of the real-world evaluation.
W2 / Q1: Test-time prompts and exclusion of GT information
Response. All main benchmark results use RAM-generated prompts derived solely from LQ images, without any GT information at inference. We adopt RAM to ensure a consistent and reproducible evaluation protocol, while Gemma can alternatively generate descriptions from LQ images and available references. During training, GT-derived prompts provide reliable semantic supervision for learning fine-grained facial attributes and text-controllable restoration. We also apply 10% text-prompt dropout to mitigate the train–test gap.
To assess prompt sensitivity, we additionally evaluate GT-derived prompts as an oracle setting. As shown in Table 1, the two prompt sources yield comparable performance, with modest perceptual improvements and nearly unchanged identity consistency under GT prompts.
Table 1. Effect of test-time prompt sources on CelebRef-HQ. LQ-derived prompts are generated using RAM for the main evaluation, while GT-derived prompts are used only for oracle analysis.
Revision. Appendix A.2 clarifies the distinction between HQ-derived training prompts and LQ-derived prompts used for the main benchmark results, which do not use GT information.
W1 / Q2: FFHQ-Ref protocol and reference counts
We evaluate on all 857 images from the official FFHQ-Ref test split using our model trained exclusively on CelebRef-HQ, without further fine-tuning. Following AdaRefSR [1], LQ inputs are generated using second-order degradation with ×4 downsampling. Consistent with the CelebRef-HQ evaluation protocol, all methods share identical pre-generated LQ inputs at 512×512 resolution. Single-reference methods use one reference, while multi-reference methods use up to four same-identity references, using all available references when fewer than four exist. Reference selections are fixed and shared across methods with the same reference count. All baselines are evaluated using their official implementations and publicly released pretrained weights.
Revision. The FFHQ-Ref evaluation protocol is clarified in Sections 4.1 and 4.2.
References
[1] Yuan Wang, Yuhao Wan, Siming Zheng, Bo Li, Qibin Hou, and Peng-Tao Jiang. Trust but verify: Adaptive conditioning for reference-based diffusion super-resolution via implicit reference correlation modeling. In The Fourteenth International Conference on Learning Representations, 2026.