- Rating
- 3(+1)
- Confidence
- 1(−1)
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies paired low-light image enhancement (LLIE), aiming to recover normally exposed images from low-light observations while preserving scene structure and details. The authors propose R2RFlow. A Retinex decomposition produces a reflectance component R and an illumination component I; R is used as the transport source, and a MeanFlow-style finite-interval operator performs one-step restoration. The model further introduces structural priors, illumination modulation, and wavelet detail fusion. Training supervises deployment, reference-intermediate, and predicted-rollout paths using restoration losses. Experiments are conducted on LOL-v1 and LOL-v2-Real. A model trained on LOL-v1 is also transferred to LSRW-Nikon and LSRW-Huawei. The paper reports main benchmark results, cross-dataset results, and ablations of source initialization, evidence conditioning, and training objectives.
Critical strengths
The problem formulation is task-aware. The paper separates the transport source from the restoration evidence: reflectance is used for initialization, while illumination, structural, and frequency information complement the restoration. This is more interpretable than simply concatenating all inputs, and Figure 2, Figure 3, Table 3, and Table 4 provide initial evidence for the design.
The experiments cover the main design components. Table 3 compares different source states, Table 4 incrementally adds conditioning modules, and Table 5 compares training objectives. The cross-dataset experiments also provide evidence beyond a single benchmark.
Critical weaknesses
The methodological contribution needs stronger justification. Section 3.1 adopts MeanFlow’s finite-interval parameterization, and Eq. (4) is a deterministic residual predictor at deployment. Table 5 provides a useful deployment-only comparison, but both auxiliary paths are added together, improving PSNR from 25.10 to 25.26 dB. This leaves their individual contributions and the benefit of learning interval transport unclear. The related-work discussion also provides little comparison with other approaches to one-step restoration.
Important experimental details are missing. The paper does not identify the Retinex decomposition checkpoint or specify the pretraining data and frozen status of the preprocessing networks. The MeanFlow baseline objective and time-sampling procedure are not fully documented. Although Section 4.1 specifies No GT-mean evaluation, the provenance of each baseline result remains unclear. Figures 2 and 3 omit the data split used for their statistics, and local structural correlation is not defined. The unresolved LOL-v1 citation and missing PSNR header in Table 3 also need correction.
Questions for authors
What distinguishes the proposed interval transport learning from restoration-supervised residual prediction? Please specify the MeanFlow baseline objective and time sampling in Table 5, and clarify the individual effects of the reference-intermediate and rollout losses.
Which checkpoints and pretraining datasets are used for the Retinex decomposition and SMG networks? Are these networks frozen, and do their training data overlap with the evaluation images?
Were the baseline results in Tables 1 and 2 obtained from checkpoints, retraining, or published numbers? Were all outputs evaluated with the same preprocessing and No GT-mean implementation?
Which data split is used in Figures 2 and 3? How is local structural correlation computed and averaged?
7 comments
Further response serve to adress reiviewer's concerns(Part 1/2)
Q3. What is the result of a direct regression model using exactly the same inputs, U-Net, parameter budget, and restoration loss? If direct regression performs similarly, how should the independent contributions of finite-interval transport and multi-path flow training be interpreted?
The “Deployment objective” in Table 5 is the same-architecture direct residual regression baseline. It retains the same inputs, conditioning pathways, U-Net, parameter budget, and restoration criterion, using only deployment endpoint supervision:
With fixed time conditions , this is a conditional residual regressor, equivalently written as .
-
In-dataset comparison (LOL-v1).
Training strategy PSNR ↑ SSIM ↑ LPIPS ↓ Residual regression / deployment-only 25.10 0.8512 0.1071 Full multi-path supervision 25.26 0.8578 0.1018 Compared with direct residual regression, the multi-path-supervised flow model achieves higher PSNR while maintaining favorable SSIM and LPIPS performance.
-
Cross-dataset comparison. Both LOL-v1-trained models are directly evaluated without target-domain fine-tuning:
Training strategy Nikon PSNR ↑ SSIM ↑ LPIPS ↓ Huawei PSNR ↑ SSIM ↑ LPIPS ↓ Residual regression / deployment-only 15.25 0.4463 0.2344 18.96 0.5987 0.3821 Full multi-path supervision 16.15 0.4728 0.2312 20.08 0.5998 0.3790 PSNR improves by 0.90 dB on LSRW-Nikon and 1.12 dB on LSRW-Huawei, with higher SSIM and lower LPIPS on both datasets.
With the source, architecture, restoration criterion, and deployment fixed, these comparisons support the additional contribution of multi-path supervision to restoration and cross-dataset generalization. Inference still requires one predictor evaluation.
We thank the reviewer for this helpful suggestion. We will explicitly identify the residual regression baseline in Table 5 and include the additional cross-dataset comparison in the revision.
Q4. How does R2RFlow differ precisely from existing conditional flow, rectified-flow, one-step restoration, and Retinex-based generative LLIE methods? Why are the closest methods not included as direct baselines or evaluated under a unified protocol?
We compare noise and observation-derived sources for paired LLIE. Among Retinex-based generators, Diff-Retinex [2] restores reflectance and illumination separately, then recombines them. Our analysis finds , while retains local structural evidence. We thus use a single reflectance-to-image transport, with illumination, structure, and high-frequency conditioning.
| Comparison | LLFlow [1] | R2RFlow (ours) | Diff-Retinex [2] |
|---|---|---|---|
| Model | Invertible flow | Interval transport | Dual diffusion |
| Source / prior | |||
| Conditioning | (respective branches) | ||
| Restored variables | |||
| Output | |||
| Restoration supervision | (per branch) |
Here, is LLFlow’s color-map-based prior mean at inference, is identity covariance, are restored normal-light components,.
We train one shared predictor through deployment, reference, and rollout restoration losses; inference uses one evaluation. LLFlow and Diff-Retinex are already evaluated on the same test images under No GT-mean (Q6); Table 5 includes a fixed-architecture MeanFlow ablation.
We appreciate this helpful feedback, which will improve the clarity of our manuscript.
[1]. Wang Y, Wan R, Yang W, et al. Low-light image enhancement with normalizing flow[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2022, 36(3): 2604-2612.
[2]. Yi X, Xu H, Zhang H, et al. Diff-Retinex: Rethinking low-light image enhancement with a generative diffusion model[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2023: 12302-12311.
Further response serve to adress reiviewer's concerns(Part 2/2)
Q5. Which exact models and checkpoints are used for D and SMG? Are they frozen? Do their pretraining data include LOL, LSRW, related test images, or datasets with overlapping scenes?
The two pretrained modules are adopted from the following works:
-
Retinex decomposition. We use the Decom-Net subnetwork of Retinex-Net, introduced by Wei et al. in Deep Retinex Decomposition for Low-Light Enhancement [1], as our decomposition module . It extracts reflectance and illumination from the low-light observation:
-
Structural prior extraction. We use the structure modeling branch (edge prediction network) of SMG, introduced by Xu et al. in Low-Light Image Enhancement via Structure Modeling and Guidance [2], to extract the structural prior:
which provides conditioning information for the main restoration network.
Training data and freezing. We adopt the architectures from these works and pretrain both modules on the corresponding benchmark training split. For LOL-v1, both Retinex and SMG are pretrained exclusively on the LOL-v1 training set; for LOL-v2-Real, both are pretrained exclusively on the LOL-v2-Real training set. After pretraining, both modules are frozen during training of the main restoration network. Their training data are therefore restricted to the respective benchmark training split, without using test images or additional external training data.
Cross-dataset evaluation. For LSRW-Nikon and LSRW-Huawei, we directly evaluate the complete LOL-v1 model: Retinex, SMG, and the main restoration network all retain the weights obtained in the LOL-v1 experiment. No component is retrained or fine-tuned on either target dataset.
We appreciate this helpful suggestion, which will improve the clarity of our manuscript. We will explicitly document the module sources, training-data scope, freezing status, and checkpoint identifiers in the revision.
Q6. Were the baseline results in Tables 1 and 2 obtained by unified retraining, official checkpoints, or numbers taken from prior papers? Were all methods evaluated with the same input resolution, preprocessing, PNG saving procedure, brightness handling, and No GT-mean implementation? Do all supervised methods in Table 2 use LOL-v1 checkpoints?
Except for the case described below, baseline results were obtained by running the publicly released official checkpoints and evaluating them on the same test images using unified evaluation code, rather than directly copying metrics from previous papers.
For RetinexNet on LOL-v2-Real, no official checkpoint trained on this dataset was available. We therefore used the official implementation and followed the training parameters of the official LOL-v1 experiment, including a batch size of 16, to train the model on the LOL-v2-Real training set and evaluate it on the corresponding test set.
All metrics are computed from saved PNG outputs under the same No GT-mean protocol. We do not rescale or correct the brightness of enhanced images using the mean intensity of the normal-light ground truth. LPIPS is consistently computed using AlexNet features. We will document each method’s input resolution, normalization and other preprocessing, output-saving procedure, and brightness handling, distinguishing model-specific input requirements from the evaluation steps shared across all results.
All supervised methods in Table 2 use their LOL-v1 checkpoints and are directly evaluated on the target datasets without target-domain fine-tuning. For R2RFlow, this setting covers Retinex, SMG, and the main restoration network: the entire system uses weights obtained in the LOL-v1 experiment.
[1]. Wei C, Wang W, Yang W, et al. Deep Retinex decomposition for low-light enhancement[C]//British Machine Vision Conference. 2018.
[2]. Xu X, Wang R, Lu J. Low-light image enhancement via structure modeling and guidance[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023: 9893-9903.
We are grateful for the reviewer's acknowledgment of our work. We have taken the time to thoroughly address your questions and have included detailed responses to clarify any uncertainties.
We thank the reviewer for pointing out these omissions. The unresolved citation marker “LOL-v1 (?)” and the missing “PSNR ↑” label in Table 3 are citation and typesetting oversights. We will provide the correct citation and fix the table header.
The analyses in Figures 2 and 3 were conducted on the training sets of LOL-v1 and LOL-v2-Real, without using test images. We denote a candidate representation by A and its paired normal-light target by X.
Pixel-space discrepancy (Figure 2). We use mean squared error:
MSE(A,X)=3HW1∑h,w,c(Ah,w,c−Xh,w,c)2.
For each image, this metric averages over all pixels and RGB channels. The results are then aggregated through weighted averaging over the LOL-v1 and LOL-v2-Real training sets. A lower value indicates greater pixel-space proximity to the normal-light target.
Local structural correlation (Figure 3). We use the local Pearson correlation coefficient:
ρw(A,X)=varw(A)varw(X)covw(A,X).
Local means, variances, and covariances are computed using a **normalized 11×11 Gaussian window **. Specifically,
μA=∑qwqAq,μX=∑qwqXq,
covw(A,X)=∑qwq(Aq−μA)(Xq−μX),
varw(A)=∑qwq(Aq−μA)2,
with the target variance computed analogously. Correlations are calculated separately for each channel and valid window, averaged within each image, and then averaged over the training images. We retain the sign without taking the absolute value or squaring the coefficient. A higher value indicates greater local structural similarity.
These analyses motivate distinguishing the transport source from complementary restoration evidence: a representation closer to the target in pixel space does not necessarily preserve all useful structural information. We will include these data splits, metric definitions, and aggregation procedures in the revised manuscript.
MeanFlow ablation (Table 5). We retain the same reflectance source and conditioning architecture. For zt=(1−t)X+tR and vc=R−X, the original MeanFlow identity [1] gives the target
utgt=sg![vc−(t−r)dtduθ(zt,t,r;C)].
The JVP tangent is (vc,1,0), with r and conditioning fixed; the target is stop-gradient. We use 75% r=t and 25% r<t samples, without an extra boundary loss. The official weighted squared error is minimized against this target. Remaining sampling settings follow the official configuration; its version and complete parameters will be documented.
Final objective.
Ltotal=E![Ldep+0.5Lint+0.5Lroll].
All paths share the same restoration criterion. The MeanFlow JVP loss is used only in the ablation, not the final objective.
Difference from endpoint regression. Endpoint regression supervises only restoration from R with (t,r)=(1,0). R2RFlow additionally restores reference and predicted intermediate states using the shared predictor. Gradients through the predicted state jointly optimize both rollout segments through the final restoration loss.
The distinction is training-state coverage, interval conditioning, and differentiable compositional supervision. Deployment retains a one-step residual form with one predictor evaluation.
We sincerely appreciate your helpful suggestion and will clarify the MeanFlow configuration in the revision.
[1]. Geng Z, Deng M, Bai X, et al. Mean flows for one-step generative modeling[C]//Advances in Neural Information Processing Systems. 2025, 38: 75460-75482.