- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper explores a method for embedding visible watermarks during diffusion model generation. The approach is primarily based on a differentiable renderer and consists of four stages (Locating, Blending, Filtering, and Embossing) that select appropriate positions for watermark embedding while minimizing the impact on image aesthetics. The proposed method is adaptable to various image and video generation models and achieves better perceptual quality.
Critical strengths
-
The problem addressed in this paper is highly important: how to add visible watermarks to images while preserving their visual quality.
-
The idea of using a differentiable renderer to embed visible watermarks is somewhat novel.
Critical weaknesses
-
The practical utility of the proposed method remains questionable. First, the method requires intervention in the diffusion model's generation process and incurs non-negligible computational overhead. The authors need to clarify what specific advantages the proposed method offers compared to post-processing watermarking algorithms, and whether these advantages are sufficient to offset the inconvenience of embedding the watermarking process into the generation pipeline. Additionally, the algorithmic pipeline designed by the authors lacks a mechanism for seamlessly integrating watermarks with the semantic content of the image, which leads readers to question whether it is even necessary to embed the watermarking process into the diffusion model's generation pipeline.
-
There is a clear lack of necessary experiments. The community already has numerous visible watermarking methods. Examples include DVW: Diffusion Visible Watermark (ACM MM 2025), Beyond Invisibility: Learning Robust Visible Watermarks for Stronger Copyright Protection (UAI 2025), and Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal (ECCV 2022). Yet the authors compare against only one baseline (Ran et al., 2025) in the main paper (Table 2), which is clearly insufficient. In addition, the ablation study provides only qualitative results in the appendix, with no quantitative results at all. Furthermore, many important experimental results that belong in the main paper are relegated to the appendix. The authors should condense unnecessary sections (e.g., the full-page Figure 2 and the overly detailed preliminaries) and allocate the freed space to these critical experiments.
Questions for authors
- Compared to post-processing watermarking algorithms, what significant advantages does the proposed method offer?
- Why does the main paper compare against only one baseline? Please explain the rationale for omitting other baselines.
- Why is the ablation study entirely qualitative?
4 comments
Rebuttal for Reviewer E4jG [2/2]
[W2a] “There is a clear lack of necessary experiments. The community already has numerous visible watermarking methods. Examples include DVW: Diffusion Visible Watermark (ACM MM 2025), Beyond Invisibility: Learning Robust Visible Watermarks for Stronger Copyright Protection (UAI 2025), and Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal (ECCV 2022). Yet the authors compare against only one baseline (Ran et al., 2025) in the main paper (Table 2), which is clearly insufficient.”
[Q2] “Why does the main paper compare against only one baseline? Please explain the rationale for omitting other baselines.”
Response. Of the three, only DVW produces a comparable output, and we now compare against it; the other two address different problems.
DVW (ACM MM 2025). No code is released, so we re-implemented it on FLUX.1-dev from the paper (same 200 prompts, logos, and six marks per image; new Table A9, App. C.4):
| NIQE↓ | ILNIQE↓ | BRISQUE↓ | Decides placement | Attribution | |
|---|---|---|---|---|---|
| DVW | 4.58 | 31.1 | 28.6 | ✗ (user-given mask) | ✗ |
| Ran et al. | 4.81 | 33.8 | 30.2 | ✓ | ✗ |
| DiffStamp | 4.63 | 30.5 | 26.2 | ✓ | ✓ |
DiffStamp is best on ILNIQE and BRISQUE and on par on NIQE. More importantly, DVW only fuses a mark into a mask the user must supply; where a mark should go, which is our central contribution, is outside its scope.
Watermark Vaccine (ECCV 2022) is not a watermarking method. It adds an imperceptible adversarial perturbation to an already-watermarked image so that removal networks fail; it neither designs nor places a mark, so it has no output to compare in Table 2. It is complementary and can be applied on top of any visible mark, including ours. On its own axis, DiffStamp already withstands all five blind removal networks we tested, with no vaccine (Table A10).
Beyond Invisibility (UAI 2025) learns the watermark pattern itself for removal robustness and overlays it on existing images. Disclosure requires a prescribed emblem (a logo or standardized mark), which a learned pattern cannot carry.
Ran et al. was chosen because it is the closest prior work: an aesthetic method that decides where a given logo goes.
[W2b] “In addition, the ablation study provides only qualitative results in the appendix, with no quantitative results at all. Furthermore, many important experimental results that belong in the main paper are relegated to the appendix. The authors should condense unnecessary sections (e.g., the full-page Figure 2 and the overly detailed preliminaries) and allocate the freed space to these critical experiments.”
[Q3] “Why is the ablation study entirely qualitative?”
Response. It no longer is. The revision adds a quantitative per-stage ablation (Table A2; one stage removed at a time, 200 images each). Detection = a GPT-5.2 judge finds ≥1 mark, before / after the strongest regeneration attack; stamp-free reference 0.43 / 0.49.
| NIQE↓ | BRISQUE↓ | Det. (0) | Det. (180) | |
|---|---|---|---|---|
| Full | 4.63 | 26.2 | 0.950 | 0.870 |
| w/o Locating | 6.69 | 46.4 | 0.995 | 0.935 |
| w/o Blending | 4.62 | 26.4 | 0.955 | 0.765 |
| w/o Filtering | 5.01 | 30.9 | 0.975 | 0.825 |
| w/o Embossing | 5.29 | 35.1 | 0.505 | 0.535 |
Each stage has a distinct, measurable role. Locating → quality: without it, stamps sit conspicuously on the content and quality collapses. Blending → robustness: +10.5 points (p=0.009) at no quality cost. Filtering → both. Embossing → visibility: without it, detection falls to the stamp-free level. The main paper now also carries the new quantitative robustness evidence: a stamp-free control with significance tests and five blind watermark removers (Table 3, Sec. 5.5).
Thank you for your detailed response. I think most of my questions have been satisfactorily addressed, so I’m willing to raise my score to 3 (Weak Accept).
Thank you for raising your score. Your review made the paper better: the DVW comparison (Table A9) clarified our scope, and the quantitative ablation (Table A2) now shows what each stage contributes.
Rebuttal for Reviewer E4jG [1/2]
Thank you for emphasizing the importance of visible watermarking and recognizing the novelty of using a differentiable renderer.
Response. Three advantages post-processing cannot offer, at +3.9–14.2% runtime and with no training (Table 4, p. 9, lines 468–478):
(Table 2, p. 8, lines 391–399; Fig. 4, p. 9, lines 432–439.)
We respectfully disagree that a semantic-integration mechanism is missing. Blending (Sec. 4.2, p. 5, lines 255–269) injects the stamp into the predicted clean image so that the remaining denoising steps harmonize the surrounding content with it. Changing content around a mark, and reading the generator’s cross-attention for attribution, are possible only inside generation (p. 1, lines 047–053). The cost is small, e.g., 23.3 s → 25.8 s per FLUX image.