- Rating
- 4(+1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper introduces AgenticShadow, a dataset of 17,138 image-mask-target triplets constructed through generative editing, automated evaluation, and regional correction. It studies the resulting supervision across several restoration models and introduces a semantic-and-depth Prior-Fusion baseline with a mask-free variant.
Critical strengths
- The dataset expands supervision to diverse general scenes, faces, and remote-sensing imagery.
- Improvements across several restoration architectures support the usefulness of the constructed training data.
- The appendix provides useful construction statistics, costs, runtime measurements, and failure analyses.
Critical weaknesses
- Evaluation relies heavily on generated references, and some benchmark inputs undergo generative preprocessing.
- Better boundary-color consistency coincides with larger changes outside shadow regions.
- The benefits of adaptive retries and the additional depth branch need stronger controlled comparisons.
Questions for authors
- Most gains in Table 4 are measured against pseudo-targets generated by the training-data workflow. Beyond ISTD+, please validate the trained models on independently captured pairs or through blinded human assessment in the new domains.
- Appendix B.3 uses GPT Image 2 to normalize benchmark inputs, which may itself change image content. Please evaluate on original images with ordinary resizing and quantify changes introduced by generative normalization.
- Despite improved CDD, Appendix B.5 reports non-shadow RGB RMSE of 23.13, versus 3.44–18.39 for previous methods. Please include this preservation issue in the main results and check whether trained models inherit these unwanted edits.
- Only 2.07% of images trigger feedback-guided retries (Table 6). Please compare against a fixed multi-candidate pipeline using the same prompts, selector, and correction under a matched editing budget to isolate the benefit of adaptive control.
- In Table 3(b), adding depth to semantic priors improves LAB RMSE only from 5.585 to 5.577. Please report variation across training seeds and the additional inference cost to establish whether the depth branch is worthwhile.
4 comments
Responses to Reviewer 3NVc’s Questions and Concerns (cont’d)
Non-shadow preservation: do trained models inherit unwanted edits? (W2, Q3)
We acknowledge that non-shadow preservation remains a limitation.
On original AgenticShadow test images, resized for SBU/CUHK, non-shadow input–prediction RGB RMSE increases from 5.93 to 16.58 for HomoFormer and from 5.78 to 18.65 for PF after combined training. On all 540 ISTD+ test images, non-shadow input–prediction RGB RMSE changes from 3.47 to 3.01 for HomoFormer and from 3.29 to 3.59 for PF. These results indicate increased non-shadow changes on AgenticShadow after combined training, while ISTD+ shows little change.
However, we also observe that non-shadow differences occur in the reference targets, even for captured datasets. Mean non-shadow input–target RGB RMSE is 10.83 on SRD and 20.29 on WSRD+, using available SRD masks and difference-based pseudo masks for WSRD+. For workflow-generated targets, the corresponding values are 13.83 on all 540 ISTD+ test images and 27.27 across all 17,138 AgenticShadow pairs. This suggests that preserving non-shadow content during generative construction is more challenging in complex real-world scenes. We have expanded the preservation analysis in Appendix B.5 and summarized the limitation in Section 5.1.
Adaptive control versus fixed multi-candidate generation (W3, Q4)
The 2.07% statistic measures only how often the major-failure retry branch is triggered, while candidate selection and regional correction still apply when the initial probe passes. Fixed multi-candidate generation alone cannot reliably replace corrective feedback, because repeated generation can retain shadow structure or produce different hallucinated content.
For four rejected-probe examples, we compare five and ten independent generations using the original prompt with three feedback-guided candidates per case, keeping inputs, masks, and model settings unchanged:
| Generation | Candidates per case | Mean CDD (×10³) ↓ | Best CDD (×10³) ↓ |
|---|---|---|---|
| Without feedback | 10 | 170.014 | 25.384 |
| Without feedback | 5 | 160.616 | 26.153 |
| With feedback | 3 | 1.121 | 0.307 |
The visual comparisons show repeated hallucinations or retained shadow structure without feedback, while feedback produces more consistent removal. We have added the numerical and visual comparisons in Appendix B.4, including Figure 13.
Depth prior's incremental gain and inference cost (W3, Q5)
We agree that depth’s incremental gain over semantic-only PF is marginal: LAB RMSE improves from 5.585 to 5.577, and from 5.607 to 5.604 with a second training seed. Depth alone still improves over the HomoFormer backbone from 5.912 to 5.769. We report full PF as the best observed configuration and provide both single-prior variants and their costs for comparison.
Inference costs are measured on RTX A6000 GPUs with 512 × 512 inputs and batch size 1, including online prior extraction where applicable:
| Configuration | AgenticShadow macro LAB RMSE ↓ | Latency (ms/image) ↓ | Peak allocated memory (GiB) ↓ |
|---|---|---|---|
| HomoFormer | 5.912 | 505.2 | 0.922 |
| Depth-only | 5.769 | 718.7 | 2.186 |
| Semantic-only | 5.585 | 572.3 | 2.073 |
| Full PF | 5.577 | 956.2 | 3.330 |
We have added the single-prior efficiency measurements in Appendix C.3.
response
Based on the author's response, I believe most of my concerns have been addressed; therefore, I am inclined to increase my rating.
Thank you for your constructive feedback and positive reassessment of our work. We are glad that our responses have addressed most of your concerns.
Responses to Reviewer 3NVc’s Questions and Concerns
Thank you for recognizing the broader supervision, improvements across architectures, and construction analysis.
Does normalization change image content, and do gains persist with ordinary resizing? (W1, Q2)
We agree that generative normalization can alter image content and introduce a potential confound. And yes, the gains persist on original images with ordinary resizing.
(1) To quantify the changes, we resize the original images to 512 × 512 and compare the differences:
(2) Testing the trained models on the original testing images give the following improvements:
We have added the normalization and original-input analyses in Appendices B.3 and D.3. The human assessment and captured-reference evaluations below provide complementary evidence.
Do gains hold on independently captured pairs and in blinded human assessment? (W1, Q1)
Yes. We validate the gains on independently captured pairs and through blinded human assessment on original inputs.
Independently captured pairs: On all 1,100 held-out WSRD+ pairs, training with ISTD+ and AgenticShadow improves PhaSR’s PSNR by 2.84 dB and reduces LAB RMSE by 30.1% compared with ISTD+-only training. These pairs were captured under controlled indoor, close-range conditions. Since WSRD+ provides no annotated shadow masks, we evaluate frozen mask-free models:
Blinded human assessment: Combined-trained PF scores 3.11/4 versus 1.89/4 for ISTD+-only PF, an average paired improvement of 1.22 points. We conduct a blinded study on 80 AgenticShadow cases using original inputs, resized for SBU/CUHK. Raters assess removal quality using a four-point scale: 1 (Very poor), 2 (Poor), 3 (Good), and 4 (Very good).
We have added the WSRD+ evaluation in Section 5.4 and the human study in Section 5.5. Generalization to unseen domains and improvements in human-rated removal quality support AgenticShadow as a valuable resource for the shadow removal community.