- Rating
- 3(+1)
- Confidence
- 4
- Informativeness
- 2(+1)
- Presentation
- 2
- Soundness
- 2(+1)
Read review
Paper summary
This paper presents Contagious Degradation Synthesis (CoDeS), a low-light image synthesis framework for object detection. The central idea is to extract seven interpretable degradation descriptors from unlabeled real low-light images and learn their joint distribution using an illumination-conditioned conditional variational autoencoder (CVAE). The sampled degradation configurations are subsequently transferred to labeled normal-light images through an image-formation-inspired rendering pipeline, allowing existing object annotations to be reused for low-light detector adaptation. The authors further introduce a lightweight Low-Light Feature Adapter (LFA) to adapt SAM 3 features to low-light conditions. Experiments on ExDark, NOD, and DARK FACE demonstrate consistent improvements over direct SAM 3 inference.
Critical strengths
-
meaningful problem formulation. The paper addresses an important limitation of existing low-light detection methods: the scarcity of annotated low-light images and the mismatch between manually designed degradation distributions and real imaging conditions.
-
An interpretable and systematic synthesis framework. CoDeS incorporates multiple degradation factors, including illumination, noise, blur, and color bias, into a unified synthesis pipeline. The use of measurable appearance descriptors provides interpretable controls over the degradation process, although the effectiveness and generalization ability to out-of-domain scenarios need further discussion.
Critical weaknesses
1. Unfair comparisons with existing methods weaken the experimental support for the main contribution.
A major concern is the fairness of the comparisons in Table 2. The proposed method employs SAM 3, a large-scale pretrained vision model, while several competing methods are evaluated using substantially smaller detection architectures, such as YOLOv3. Consequently, the considerable performance improvements over existing methods may be largely attributable to differences in backbone capacity and pretraining rather than the proposed degradation synthesis strategy.
Notably, the improvements over direct SAM 3 inference are relatively modest (2.8–3.2 mAP50 points), compared with the much larger margins reported against conventional domain adaptation methods. Although the supplementary experiments demonstrate the applicability of CoDeS to additional detection architectures, they do not fully resolve this comparison issue.
The authors are encouraged to provide comparisons with representative competing methods under the same detection backbone, initialization, and training protocol. Without such controlled experiments, it remains difficult to determine whether CoDeS genuinely advances the state of the art in low-light domain adaptation.
2. Oversimplified appearance modeling and limited novelty in degradation prior learning.
The proposed degradation prior represents each low-light image using only seven image-level scalar descriptors. However, real-world low-light degradation is inherently spatially heterogeneous. Illumination, noise, color shifts, and blur can vary substantially across image regions and exhibit complex spatial dependencies. For example, different light sources may produce locally varying color casts, while sensor noise is closely related to local signal intensity.
Although the renderer introduces spatially varying illumination fields and signal-dependent noise, these local degradation patterns are not explicitly learned from the target images. Instead, the CVAE models only the joint distribution of global descriptors, while much of the spatial variation is introduced through predefined rendering rules. This raises concerns about whether the resulting synthesis can adequately reproduce the local degradation characteristics and spatial correlations observed in real low-light images. Besides, extracting a sequence of parameters to depict low-light condition is not novel, as ELVIS [CVPR'26] (ELVIS: Enhance Low-Light for Video Instance Segmentation in the Dark) has proposed a similar method.
Furthermore, the use of a conventional CVAE to model a low-dimensional parameter distribution offers limited methodological novelty. The authors should provide stronger evidence that this formulation is necessary and sufficiently expressive compared with simpler statistical models. Otherwise, the whole framework seems to be an incremental combination of existing techniques.
3. Insufficient interpretation and justification of the illumination modes.
The illumination modes play a central role in the proposed conditional degradation prior, but their interpretation and necessity are not sufficiently established. Section 3.2 defines these modes using K-means clustering based on brightness and shadow contrast. However, it remains unclear whether clustering in this two-dimensional space can meaningfully distinguish the diverse illumination conditions encountered in real-world environments.
Table 6 demonstrates that three illumination modes achieve the best detection performance across the evaluated datasets. Nevertheless, this empirical observation alone does not explain the physical meaning of the discovered modes or their stability across datasets. A more detailed characterization of the illumination clusters, including representative image examples and their associated degradation statistics, would help justify the proposed conditional modeling strategy.
4. Target-specific degradation fitting raises concerns about cross-domain generalization.
The proposed framework learns a separate degradation prior from unlabeled training images of each target dataset and subsequently synthesizes training samples that approximate the corresponding target appearance distribution. While this setting is valid for unsupervised domain adaptation, it introduces a strong dependence on the availability and representativeness of target-domain observations.
As a result, the current experiments primarily demonstrate target-specific adaptation rather than the transferability of the learned degradation representation. The method may be sensitive to changes in illumination conditions, camera characteristics, or noise distributions that are not adequately covered by the target images used for prior fitting.
Cross-dataset generalization experiments would be particularly valuable. For example, the degradation prior could be learned from one low-light dataset and then used to train a detector evaluated on another dataset without refitting the prior. Such experiments would clarify whether CoDeS learns reusable degradation characteristics or primarily matches the statistics of a particular target domain.
5. Limited improvements from CVAE-based sampling and insufficient statistical validation.
Table 5 shows that empirical sampling of degradation vectors from real target images already provides substantial performance improvements. Replacing empirical sampling with the proposed CVAE yields an additional gain of only 0.5–0.9 mAP50 points on ExDark, depending on whether the LFA is enabled.
Given that learning the joint degradation distribution is presented as a central contribution, these relatively small gains warrant further investigation. Comparisons with simpler density estimators, such as Gaussian mixture models, as well as multiple-seed evaluations, would help establish whether the learned CVAE prior offers a statistically reliable and meaningful advantage.
In addition, the current distributional visualization mainly focuses on brightness and shadow contrast. More direct evaluations of the full seven-dimensional distribution and the dependencies among degradation factors would strengthen the technical justification.
Questions for authors
-
[The most important one] Can the authors provide a fair comparison with representative low-light domain adaptation methods using the same detector backbone, pretrained initialization, and training schedule?
-
Given that the degradation prior consists of image-level scalar measurements, how can the method represent spatial dependencies among illumination, noise, color shifts, and blur? Can the authors provide quantitative evidence that the synthesized local degradation patterns match those observed in real low-light images?
-
What is the physical interpretation of the three illumination modes in Table 6? Can representative examples and degradation statistics be provided to explain the distinctions between these modes?
-
How well does a degradation prior learned from one target dataset generalize to another low-light dataset without refitting? Can the authors provide cross-dataset evaluation results?
-
How does CVAE-based sampling compare with simpler alternatives, such as Gaussian mixture models? Are the relatively small improvements over empirical sampling consistent across multiple random seeds?
-
The paper uses labeled target validation data for checkpoint and configuration selection. Can the authors clarify whether the competing methods follow the same model-selection protocol and provide results under a target-label-free selection strategy?
9 comments
Response to Reviewer vhZ1 (Part 2/3)
Q3: What is the physical interpretation of the three illumination modes in Table 6? Can representative examples and degradation statistics be provided to explain the distinctions between these modes?
A3: The three modes describe illumination conditions through overall brightness and shadow contrast . Lower indicates darker appearance, while larger indicates a stronger separation between mid-tones and deep shadows. Taking ExDark as an example, with the labels used in Figure 5:
- C1: strong shadows, with illuminated regions surrounded by deep shadows, such as scenes lit by windows or vehicle headlights.
- C2: relatively brighter scenes with milder shadows, where more of the scene remains visible.
- C3: overall darker scenes, such as dim interiors and nighttime environments.
We summarize their degradation statistics below as mean ± standard deviation.
| Descriptor | C1 () | C2 () | C3 () |
|---|---|---|---|
| Brightness | |||
| Shadow contrast | |||
| Visible noise | |||
| Blur | |||
| Spatial illumination variation |
Statistics use valid estimates; the valid counts for are 705, 1,332, and 819, respectively. C1 and C2 mainly differ in shadow contrast, whereas C2 and C3 mainly differ in overall brightness. These complementary conditions provide an interpretable structure for learning how degradation factors vary across illumination regimes. We will include these descriptions and statistics in the revised paper.
Q4: How well does a degradation prior learned from one target dataset generalize to another low-light dataset without refitting? Can the authors provide cross-dataset evaluation results?
A4: We evaluate ExDark→NOD transfer by freezing the ExDark degradation prior and the complete CoDeS model trained with it. We directly test this model on all NOD test images, without refitting the prior, fine-tuning the detector, or selecting checkpoints using NOD validation results.
| Evaluation setting | NOD mAP50 (%) |
|---|---|
| Pretrained SAM 3 | 60.6 |
| CoDeS: ExDark→NOD | 61.9 |
| CoDeS: NOD-specific adaptation | 63.4 |
The frozen ExDark model improves over pretrained SAM 3 by 1.3%, with a gap of 1.5% to NOD-specific adaptation. These results demonstrate that the CoDeS model trained with the ExDark prior transfers useful low-light detection capability to NOD without additional fitting or adaptation. We will include this cross-dataset evaluation in the revised paper.
Response to Reviewer vhZ1 (Part 3/3)
Q5: How does CVAE-based sampling compare with simpler alternatives, such as Gaussian mixture models? Are the relatively small improvements over empirical sampling consistent across multiple random seeds?
A5: We add a three-component, full-covariance GMM comparison on ExDark. The same-seed comparison below combines the original Table 5 Empirical/CVAE results with the supplementary GMM evaluations.
| Sampling strategy | Without LFA: mAP50 (%) | With LFA: mAP50 (%) |
|---|---|---|
| Empirical | 79.1 | 80.0 |
| GMM | 78.7 | 79.9 |
| CVAE | 79.6 | 80.9 |
We can find that CVAE achieves the highest mAP50. Its gains over GMM and empirical sampling are 0.9 and 0.5 percentage points without LFA, increasing to 1.0 and 0.9 percentage points with LFA. These results support the effectiveness of the learned illumination-conditioned prior and its complementary contribution alongside LFA.
We further report the original paper seed and two supplementary training seeds, all without LFA.
| Sampling strategy | 20260621 (paper) | 8675309 | 104729 |
|---|---|---|---|
| Empirical | 79.1 | 77.9 | 78.6 |
| CVAE | 79.6 | 78.4 | 79.2 |
We can see that CVAE is higher in these three displayed entries.
Q6: The paper uses labeled target validation data for checkpoint and configuration selection. Can the authors clarify whether the competing methods follow the same model-selection protocol and provide results under a target-label-free selection strategy?
A6: We reran IAT, YOLA, and FRBNet with SAM 3 while retaining their low-light modules. All methods use real ExDark training images without synthetic data. For these three baselines, we use checkpoints saved after a fixed number of training epochs. Their results are reported below.
| Method | mAP50 (%) |
|---|---|
| IAT + SAM 3 | 84.9 |
| YOLA + SAM 3 | 82.3 |
| FRBNet + SAM 3 | 85.0 |
| Ours | 86.7 |
Target training detection annotations are not used for prior fitting or detector optimization. For the ExDark ablation in Table 5, all trained variants are evaluated using checkpoints from the same fixed training epoch. The fixed checkpoint also coincides with the validation-best checkpoint in this ablation, so the fixed-epoch rule retains the reported results below. We will clarify this checkpoint-selection protocol in the revised paper.
| Training strategy | LFA | mAP50 (%) |
|---|---|---|
| Pretrained SAM 3 (direct inference) | ✗ | 77.7 |
| Empirical sampling | ✗ | 79.1 |
| Empirical sampling | ✓ | 80.0 |
| CVAE generation | ✗ | 79.6 |
| CVAE generation (CoDeS) | ✓ | 80.9 |
Response to Reviewer vhZ1 (Part 1/3)
We thank the reviewer for the constructive comments and helpful suggestions!
Q1: [The most important one] Can the authors provide a fair comparison with representative low-light domain adaptation methods using the same detector backbone, pretrained initialization, and training schedule?
A1: We add an ExDark comparison by adapting AT, 2PCNet, and ISP-Teacher to SAM 3 while retaining their adaptation mechanisms. These baselines use the same official SAM 3 pretrained initialization, frozen image/text encoders, optimizer, and learning-rate schedule as CoDeS. No target training detection annotations are used. Test mAP50 results are reported below.
CoDeS exceeds AT, 2PCNet, and ISP-Teacher by 1.1, 2.5, and 1.9 percentage points, respectively, with the same SAM 3 backbone and pretrained initialization. We will include this comparison in the revised paper.
Q2: Given that the degradation prior consists of image-level scalar measurements, how can the method represent spatial dependencies among illumination, noise, color shifts, and blur? Can the authors provide quantitative evidence that the synthesized local degradation patterns match those observed in real low-light images?
A2: The CVAE learns the joint distribution of degradation descriptors measured from real low-light images, including how these factors vary together under different illumination conditions. Sampling from this learned prior guides synthesis toward the degradation characteristics of real low-light images, while the renderer realizes their spatial effects. The illumination scalar a controls a smooth field Fsp(p)∝2aP(p), where P(p) is a smooth random field. Noise includes a local-luminance-dependent term and a row-correlated component. Chromatic gains and blur act on the spatially modulated image before exposure and noise are applied (Appendix A.3).
We evaluate local patterns on DARK FACE using 2,400 real images and 2,400 synthetic images per method. Alongside multiscale Lab-patch SWD, we compare spatial correlation curves of regional brightness, noise residuals, chromaticity, and edge smoothness across horizontal and vertical offsets. Spatial error below is the RMS difference from the real-image correlation curves.
CoDeS reduces Lab-SWD by 39.5% relative to DEN and achieves the second-lowest spatial error at both grid sizes. The mean within-image Spearman correlation between local brightness and noise residuals is 0.8194 for CoDeS versus 0.8123 for real images on the 8×8 grid; the corresponding 4×4 values are 0.8204 and 0.7932. These results provide quantitative support for the local appearance, brightness-dependent noise, and regional spatial structure produced by CoDeS. We will include these analyses in the revised paper.