- Rating
- 3
- Confidence
- 2
- Informativeness
- 3
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper targets controllable low-light image enhancement. The authors propose an EPAS that separates correction from semantic control through a gain field and a control map. The gain field allows spatially varying corrections, while the control map specifies where and how strongly to apply them. The authors train the gain predictor using targets selected through photometric search and VLM assessment. The controlled preview and spatial conditions then guide an adapted image editor. The authors evaluate the same trained model across several low-light datasets and test its global and local enhancement control.
Critical strengths
-
The authors propose a straightforward representation that separates image-dependent correction from semantic control through a gain field and a control map. This allows the same inferred correction to be applied to different selected areas at different strengths.
-
The experimental results demonstrate global and local enhancement control with competitive enhancement performance. The same trained model works across several datasets without dataset-specific retraining or fine-tuning, showing its usefulness under different low-light conditions.
Critical weaknesses
-
The accuracy of the inferred gain field needs more evidence. The gain predictor is trained using targets selected through photometric criteria and VLM assessment. However, the current experiments do not directly show whether the predicted gain provides an appropriate correction before generative restoration. Can the authors evaluate the predicted gain or the full-gain preview against paired normal-light references? This would help establish whether the gain itself provides a suitable correction or whether the editor also compensates for inaccurate predictions.
-
The roles of the learned membership maps and the choices in the search procedure need more analysis. The authors use five soft membership maps, but do not show what they learn or explain how the number was chosen. Can the authors visualize the individual maps, analyze what they learn, and explain why five maps are used? The nine-transition MH search proposes updates to the first four parameter vectors twice and the fifth only once. Why does the search use nine transitions, and why does it stop before completing the second pass?
Questions for authors
-
Please see my question in Weakness 1.
-
Please see my questions in Weakness 2.
-
Can the authors compare with an image editor adapted using the preview and fixed prompt, but without the additional spatial conditioning? For example, the editor could be adapted using LoRA. This would clarify the contribution of the explicit conditioning beyond adapting the editor to restore the preview.
-
Can the authors show examples of more than two entities at different enhancement levels? For example, one object at level 1, another at level 3, and the background at level 2. The formulation supports this setting, but the presented local examples only show two entities.
-
I would suggest that the authors include an explicit section to discuss the limitations of the method, analyze failure modes, and discuss future directions.
3 comments
Follow-up
First, thank you for the clarifications and additional experiments addressing my questions. These additions strengthen my recommendation for weak acceptance.
I have three follow-up suggestions regarding Q2 and Q4:
-
Q2: For the membership maps in Fig. 15, can the authors visualize the individual soft masks instead of the unified overlaid map?
-
Q2: Following the clarification of the search strategy, I am wondering whether more exploration of the search space would provide further benefits, since the current strategy outperforms greedy search. Could the authors consider: (1) choosing four candidates at post-burn-in transitions 60, 120, 180, and 240 instead of 237, 238, 239, and 240; and (2) always sampling around the initial prediction instead of the previously accepted state?
-
Q4: For multi-region control, can the authors report the distribution of region counts in training and testing?
Follow-up on Membership Visualization, Search Strategy, and Region-Count Statistics
Thank you for your positive assessment and for acknowledging the clarifications and additional experiments. We are pleased that these additions have addressed many of your concerns and strengthened your recommendation. We also appreciate your further suggestions, which help us better examine the search strategy and clarify the evidence for regional control. We address your follow-up comments below.
[Q2-1] Visualization of individual soft membership masks
Thank you for suggesting this clearer visualization. We have updated Figure 15 in the revised manuscript to include the five individual soft membership masks for each example, shown in the second and fourth rows. All masks use a shared color scale from 0 to 1, with dark purple indicating low membership weights and yellow indicating high weights. This presentation makes the spatial contributions and overlap of the individual memberships easier to inspect. We have also revised the accompanying discussion and figure caption accordingly.
[Q2-2] Further exploration of the search space
Thank you for these suggestions. Figure 7 shows diminishing returns from increasing or around the adopted setting under the original search strategy. Your suggestions examine complementary aspects of exploration: candidate retention and proposal centering.
To investigate these aspects within the rebuttal time budget, we trained the first-stage predictor on the same 50% subset of the DIV2K-derived training data under matched training settings, while keeping the second-stage editor fixed. The table below reports final-output performance on the LOLv1 and LSRW test sets.
(i) Spaced retention. Retaining states at transitions 60, 120, 180, and 240 yields performance close to the original strategy, with no consistent advantage across metrics. In the spaced-retention pool, the state at transition 240 was selected for 74% of the evaluated images. This suggests that selection often favors the final state despite access to earlier candidates, helping explain why broader temporal coverage provides limited additional benefit.
(ii) Initial-centered proposals. This variant performs worse on both datasets. Proposals centered at the current chain state allow accepted updates to accumulate, enabling successive moves away from the initialization. Repeatedly centering proposals at the initial prediction restricts this cumulative exploration and may make search quality more sensitive to the initial prediction, particularly when suitable corrections lie beyond its immediate neighborhood. The results are consistent with a benefit from progressively refining the initial prediction through accumulated updates.
| Search variant | Proposal center | Retained post-burn-in transitions | LOLv1 PSNR ↑ | LOLv1 LPIPS ↓ | LSRW PSNR ↑ | LSRW LPIPS ↓ |
|---|---|---|---|---|---|---|
| Original strategy | Current chain state | 237, 238, 239, 240 | 19.783 | 0.184 | 18.147 | 0.326 |
| Spaced retention | Current chain state | 60, 120, 180, 240 | 19.746 | 0.182 | 18.164 | 0.329 |
| Initial-centered proposals | Initial prediction | 237, 238, 239, 240 | 19.218 | 0.207 | 17.592 | 0.354 |
[Q4] Distribution of semantic region counts
Thank you for requesting these statistics. We summarize below the semantic region counts in the Light100K training and held-out testing data used for the second-stage regional-control experiments. Each entry reports the number of images and its percentage within the corresponding split.
| Data split | Total samples | 1 region | 2 regions | 3 regions | ≥4 regions |
|---|---|---|---|---|---|
| Light100K training | 2756 | 344 (12.48%) | 226 (8.20%) | 542 (19.67%) | 1644 (59.65%) |
| Light100K held-out testing | 700 | 90 (12.86%) | 31 (4.43%) | 85 (12.14%) | 494 (70.57%) |
Thank you again for your thoughtful suggestions and continued discussion. They have been valuable in identifying where additional evidence and clearer explanations would strengthen the paper.
We sincerely appreciate your insightful comments, which have greatly contributed to improving our work. We address your concerns as follows.
[W1, Q1] Accuracy of the predicted gain field
To evaluate the correction provided by the predicted gain field G, we added Table 4 to the main paper (see the manuscript for detailed evaluation settings) and Figure 17 to the appendix, comparing each stage against normal-light references. The full-gain preview substantially improves PSNR (7.773 → 20.098 dB) and reduces low-frequency color error ΔE00LF (36.627 → 8.766). Figure 17 shows reduced noise and color blotches after editing, with broadly similar overall tones, consistent with improved LPIPS (0.301 → 0.161) and reduced high-frequency luminance error (0.028 → 0.014). These results support that the preview provides suitable brightness and color correction, while the editor mainly complements it by suppressing noise and artifacts, with minor photometric refinement.
Your question drew our attention to the need for more direct evidence of gain prediction accuracy. The new reference-based evaluation has helped us better establish the effectiveness of photometric correction before generative restoration and clarify how the two stages contribute to the final result.
[W2, Q2] Learned memberships and search configuration
(i) Learned memberships. Figure 15 visualizes the five learned membership maps (K=5) in different colors. They capture photometric variation beyond semantic boundaries, distinguishing differently illuminated areas within an object and grouping similarly illuminated areas across objects.
(ii) Search configuration clarification. Regarding the search configuration, our original wording was imprecise: “five transitions” meant five burn-in updates per region (B=5), totaling 25 transitions, while “four consecutive states” referred to the last four retained states (N=4), which join the initial prediction to form five candidates. We also failed to explicitly report the 240 post-burn-in transitions (T=240). We apologize for the resulting confusion and have corrected Appendix B.2 to clearly specify the full MH sampling procedure.
(iii) Trade-off and sensitivity analyses. We added a performance–cost trade-off analysis for K,T and a sensitivity analysis for B,N in main-paper Figure 7 and Table 5, respectively. Figure 7 shows diminishing returns near K=5 and T=240, supporting this balance between correction flexibility and search cost. Table 5 shows that increasing B beyond five or doubling N provides no consistent improvement.
[Q3] Contribution of explicit spatial conditioning
We added Figure 18 and Table 11 (reproduced below) in Appendix F.1, comparing full EPAS with the same base editor adapted using LoRA with the preview and fixed restoration prompt, without additional spatial conditioning. Full EPAS improves all reported metrics, reducing LPIPS from 0.216 to 0.161 on LOLv1 and from 0.391 to 0.303 on LSRW. Figure 18 shows hallucinated details and color distortion in the preview-only LoRA outputs. These results support the value of explicit spatial conditioning in improving restoration quality, suppressing hallucinated details, and reducing color distortion.
[Q4] Multi-region control at different enhancement levels
Thank you for the suggestion. We added Figure 14 to the appendix to demonstrate simultaneous brightness control over three semantic regions at different enhancement levels in indoor and outdoor scenes.
[Q5] Limitations and future directions
We appreciate this recommendation. We added Appendix H to discuss grounding and segmentation errors under severe darkness, local detail hallucinations, and future directions for improving region identification and restoration fidelity.
Thank you again for your thoughtful and constructive suggestions. These additions have improved both the clarity of our methodology and the completeness of our experiments. Your feedback has been genuinely helpful in bringing the paper to a more mature form, and we hope the revised version merits your continued support.