- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
The paper presents RISE for unsupervised low-light image enhancement. It models spatial illumination adjustments and global exposure separately in log-gain space. Several bright, spatially dispersed patches are selected as Key Illumination Cues, and their brightness differences and distances to other regions are used to build the gain field. For training, the authors introduce DMER, which combines two metering rules to produce an exposure reference from each input image, without paired normal-light supervision.
Critical strengths
- RISE is trained only on LSRW-Nikon, yet exceeds the compared prior unsupervised methods in PSNR on six of seven paired benchmarks. It also achieves the highest reported IQA and IAA scores on the five unpaired datasets.
- DMER provides training guidance without paired normal-light images or external learned priors.
Critical weaknesses
- In the figure, features from the original image are used to predict the KIC target luminance, which is then fed into the structural branch; however, Appendix A.6 states that the relative branch receives only normalized information.
2 . The paper uses a default patch size of 75 × 50 pixels, but does not clarify whether this size applies to the original images or to images resized to a common resolution, nor whether it is adjusted according to the input resolution.
-
It is suggested that the training dataset, evaluation dataset, and data splits be specified in the ablation section or table captions.
-
DMER directly generates an enhanced reference image and uses it to constrain the output luminance, patch gains, and KIC luminance of RISE, but Table 9 shows that RISE† achieves higher PSNR than this reference. This result is not contradictory, but the current experiments do not sufficiently explain where the additional gains come from.
-
Eq. (1) adds epsilon only to the denominator. Therefore, when the mean luminance of a patch is P(p) = 0, log 0 still occurs, and the output is not guaranteed to be finite.
Questions for authors
-
Under what conditions does the bright-region proxy fail? Please group the cases by saturation ratio, specular reflections, noise in dark regions, and dynamic range, and compare reliability-based selection strategies.
-
Do the image features at the KICs and the predicted target luminance in Fig. 3 introduce absolute exposure information into the structural branch? How are they normalized?
-
Which statistics are included in c_scene, and what interpolation method does Up use?
-
What are the architectures of the image encoder and the illumination encoder, respectively?
-
The definition of Γ(·) and the value of τ_abs in Eq. (6) are not provided.
8 comments
[2/2] Response to Questions for Authors
To Q1:
Following your suggestion, we added experiments grouped by saturation ratio, specular reflections, noise in dark regions, and luminance range. We compared random selection, bright region selection, reliability filtering, and soft weighting. Bright KIC selection achieves the lowest MAE in all groups except the highest noise quartile, where its MAE is only 0.0027 higher than soft weighting. This indicates that reliability weighting provides a modest improvement, while bright region selection remains competitive under the tested high noise conditions.
Table 6. MAE comparison of KIC selection. Lower is better.
| Group | Count | Random | Bright | Hard | Soft |
|---|---|---|---|---|---|
| Sat. ≤1% | 129 | 0.0831 | 0.0830 | 0.0850 | 0.0842 |
| Sat. >1% | 6 | 0.0707 | 0.0596 | 0.0719 | 0.0705 |
| No specular | 110 | 0.0874 | 0.0865 | 0.0914 | 0.0906 |
| Specular | 25 | 0.0611 | 0.0525 | 0.0535 | 0.0532 |
| Noise Q1 | 34 | 0.0905 | 0.0733 | 0.0752 | 0.0771 |
| Noise Q4 | 34 | 0.0682 | 0.0699 | 0.0708 | 0.0672 |
| Range Q1 | 34 | 0.0897 | 0.0866 | 0.0871 | 0.0874 |
| Range Q4 | 34 | 0.0919 | 0.0729 | 0.0771 | 0.0732 |
Count denotes the number of images. Sat. denotes the saturation ratio. Noise refers to noise in dark regions, and Range denotes the luminance range. Q1 and Q4 denote the lowest and highest quartiles. Hard and Soft denote filtering and weighting using reliability scores, respectively.
To Q2:
KIC target luminance is jointly predicted from original image features and relative illumination features. The relative illumination representation is obtained through mean normalization as defined in Eq. (1). The structural branch receives the normalized relative illumination representation and the predicted KIC target luminance, without directly receiving original image features or raw luminance values. KIC target luminance represents the desired luminance after enhancement and provides a target reference for predicting the coefficients of propagation relationships. Therefore, using this target is not equivalent to directly introducing the original exposure level into structural modeling. Scale equivariance regularization further promotes the separation of structure and exposure.
To Q3:
The scene statistics vector contains three statistics, namely the logarithm of the mean relative luminance of the three KIC anchors, the standard deviation of log relative luminance across the entire image, and the range of log relative luminance among the three KIC anchors. uses bilinear interpolation.
To Q4:
The image encoder and illumination encoder share the same architecture but have independent parameters. The image encoder takes a three channel RGB image, while the illumination encoder takes a single channel relative log luminance map . Both encoders contain three stages with 16, 32, and 64 channels, respectively. Each stage consists of a double convolution block and a residual block, using convolutions and LeakyReLU. The last two stages downsample through convolutions with a stride of 2. The first stage produces local features, while the final stage output undergoes global average pooling to obtain global features.
To Q5:
takes the minimum of the target exposure gain and the highlight protection gain , where denotes the 99th percentile of the input luminance. This keeps the 99th percentile luminance of the absolute exposure reference at or below 0.92, leaving headroom below the saturation value of 1. We set the absolute exposure target to , where is the middle gray reference. This choice is consistent with the luminance key values used by Reinhard et al. and provides a luminance target above the middle gray reference for low light enhancement.
Dear Reviewer 3vNh,
I hope this message finds you well. As the discussion period is nearing its end with less than four days remaining, I wanted to ensure we have addressed all your concerns satisfactorily. If there are any additional points or feedback you'd like us to consider, please let us know. Your insights are invaluable to us, and we’re eager to address any remaining issues to improve our work.
Thank you for your time and effort in reviewing our paper.
[1/2] Response to Critical Weaknesses
We appreciate your valuable feedback. We hope the following clarifications and additional results address your concerns. W = Critical Weaknesses, Q = Questions For Authors.
To W1:
Thank you for pointing out this ambiguity. We intended to state that relative illumination relationships are modeled using normalized information from the relative illumination map, without directly receiving original image features or global luminance statistics. The KIC target luminance predicted from original image features is still provided to the structural branch as anchor information, so this branch does not rely solely on normalized information. We have revised lines 811 to 813 of the revised manuscript and marked the changes in red.
To W2:
Thank you for pointing out this lack of clarity. All input images are processed at their original resolutions without resizing to a common resolution. The patch size is fixed at 75 × 50 pixels across all datasets and input resolutions and is not adjusted according to image resolution.
To W3:
Thank you for the suggestion. In the original submission, we listed the training datasets used by all compared methods in Appendix C.1, Table 10, due to limited table space. Following your suggestion, we have added details of the evaluation datasets and data splits in lines 972 to 974 of this section in the revised manuscript to further improve the clarity and reproducibility of our experiments.
To W4:
DMER provides soft exposure supervision rather than an upper bound on enhancement quality. RISE does not simply replicate the handcrafted reference image. Instead, joint optimization with DMER exposure supervision, relational modeling based on KIC anchors, and multiple regularization objectives enables the network to learn spatially varying illumination corrections and achieve better enhancement than the reference itself.
Existing ablation experiments further clarify the sources of these gains. On LSRW-Nikon, Table 9 reports a PSNR of 16.297 dB for the DMER reference, while full RISE achieves 16.71 dB. Table 4(c) shows that removing the relative illumination structure or scale equivariance regularization reduces PSNR to 15.16 dB and 16.04 dB, respectively, both below the DMER reference. Table 4(a) also supports the effectiveness of each relational modeling term. Together, these results support the explanation that relative illumination modeling and regularization jointly contribute to the gains beyond the handcrafted reference.
To W5:
Thank you for pointing out this issue. Our implementation already includes the numerical stabilizer ϵ in both the numerator and denominator. However, due to an oversight related to experience during manuscript preparation, we omitted the stabilizer from the numerator in Eq. (1). We have corrected this error in the revised manuscript.