- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies watermark injection into feed-forward 3DGS models. It freezes the feature, depth, and opacity branches and fine-tunes only the Gaussian prediction head to embed a specified 48-bit message in the rendered outputs. The method selects carriers based on the original Gaussians' opacity and coverage across target views, restricts modifications through masked mixing of the original and adapted heads' outputs, and jointly uses BCE, a bit-level margin loss, and rendering-fidelity losses.
Critical strengths
-
The paper introduces a simple and interpretable local adaptation mechanism for feed-forward Gaussian prediction. Equation (10) directly retains the original head's predictions at non-carrier locations, constraining modifications in output space despite shared model parameters.
-
The experiments show consistent improvements in the recovery–fidelity trade-off across two backbones and two datasets, with limited additional overhead.
Critical weaknesses
-
There is a substantial gap between the central framing as a “model-level attack” and the scope of the empirical validation. Appendix A.2 explicitly states that the adapted model is specific to the current scene and that the original head parameters are restored after each scene. Thus, the experiments do not establish a model-level attack that is implanted once and remains effective on future unseen scenes.
-
Per-scene optimization is a valid setting in itself. However, if the evaluation views also participate in optimization, the current results establish only that the watermark can be embedded in the training views. This distinction determines the security implications of the work and the extent of its contribution relative to scene-level watermarking methods.
-
Equation (11) adds the margin loss to BCE. After the margin gradient vanishes for correctly decoded bits, BCE continues to drive optimization. Therefore, the claim that this objective “prevents excessive optimization of correctly decoded bits” does not follow directly from the stated formulation.
Questions for authors
- How are the numbers of scenes and messages, as well as the actual evaluation views, determined for Table 1? Are the three target views used for carrier selection, optimization, and final evaluation? Please provide results with an explicit separation between optimization and test views.
- Please specify the reference images used for each image-quality metric in Tables 1 and 3, and report PSNR/SSIM/LPIPS directly comparing renders before and after watermarking.
- How do random masks and opacity-only masks perform under the same BCE-plus-margin objective? Please also explain how the margin term suppresses excessive optimization when BCE remains active.
2 comments
Reply to Q1 & Q2 & Q3
Q1-(3): Does recovery depend on the original message? The original evaluations use one fixed 48-bit target message shared across all scenes. We additionally sample five independent target messages and repeat adaptation separately for each sampled message. Exact recovery is the percentage of evaluated renderings with all 48 bits correctly decoded. Mean bit error is the average Hamming distance between the decoded and target messages per rendering. The final row reports the mean and sample standard deviation across the five messages. Exact recovery ranges from 86.02% to 95.00%, with a mean of 91.12%, supporting adaptation to multiple target messages under the evaluated protocol. Figure 12 in Appendix B.10 shows renderings and pixel-wise residual maps for the default message and the five sampled messages in the revised paper.
Default: 111010110101000001010111010011010100010000100111
Message 1: 100100001111101001010001100110101010110001111111
Message 2: 011000111000111001000101011011001001100111101101
Message 3: 111111100001111111101110011000000011100100111010
Message 4: 000101111010111110111100001001001101100101100111
Message 5: 000010000101100100001101101001000100100001110010
| Target message | Bit Acc. (%) | Exact recovery (%) | Mean bit errors |
|---|---|---|---|
| Message 1 | 99.79 | 91.67 | 0.1000 |
| Message 2 | 99.90 | 95.00 | 0.0500 |
| Message 3 | 99.62 | 86.02 | 0.1833 |
| Message 4 | 99.86 | 93.33 | 0.0667 |
| Message 5 | 99.69 | 89.58 | 0.1500 |
| Mean ± std | 99.77 ± 0.12 | 91.12 ± 3.49 | 0.1100 ± 0.0560 |
Q2: References for image-quality metrics and direct before/after comparison.
Thank you for requesting clarification. All PSNR/SSIM/LPIPS values reported in the paper, including Tables 1 and 3, are computed against the corresponding ground-truth images (GT). In each model block of Table 1, the first row reports rendering quality before watermarking, while the second and third rows report quality after watermarking using Unrestricted Fine-tuning and Carrier-Restricted Fine-tuning, respectively. Carrier-Restricted Fine-tuning achieves better rendering quality than Unrestricted Fine-tuning across both datasets and models.
We additionally quantify watermark-induced changes by directly comparing paired watermarked and original-model renderings at identical camera poses. This new comparison uses the original rendering, rather than GT, as its reference. The results below report PSNR / SSIM / LPIPS, and the after-watermarking results use carrier-restricted fine-tuning.
| Dataset | Model | Before watermarking vs. GT | After watermarking vs. GT | After watermarking vs. Before watermarking |
|---|---|---|---|---|
| RealEstate10K | MVSplat | 26.36 / 0.868 / 0.129 | 26.20 / 0.864 / 0.137 | 41.79 / 0.994 / 0.016 |
| ACID | MVSplat | 28.21 / 0.842 / 0.145 | 28.00 / 0.837 / 0.158 | 42.69 / 0.990 / 0.034 |
| RealEstate10K | IDESplat | 27.84 / 0.893 / 0.108 | 27.66 / 0.888 / 0.116 | 44.41 / 0.995 / 0.010 |
| ACID | IDESplat | 29.09 / 0.859 / 0.130 | 28.78 / 0.851 / 0.146 | 42.03 / 0.988 / 0.036 |
Q3: Equal-budget carrier baselines and the BCE-plus-margin objective.
Q3-(1): How do random and opacity-only masks perform? Our original ablation evaluates the overall carrier mechanism. We add comparisons among random selection, opacity-only ranking, observability-only ranking, and joint opacity–observability ranking. The four ranking methods have the same number of carriers within each scene: mean 90,970.72, range 80,819–91,750. Joint ranking achieves the highest observed bit accuracy and exact recovery. Compared with observability-only ranking, it increases bit accuracy from 99.84% to 99.88% and exact recovery from 92.89% to 94.67%, corresponding to gains of 0.04 and 1.78 percentage points, respectively.
| Carrier selection | Mean number of carriers | Bit Acc. (%) | Exact recovery (%) |
|---|---|---|---|
| Random eligible Gaussians | 90,970.72 | 91.73 | 85.21 |
| Opacity-only ranking | 90,970.72 | 98.05 | 90.66 |
| Observability-only ranking | 90,970.72 | 99.84 | 92.89 |
| Joint opacity–observability ranking | 90,970.72 | 99.88 | 94.67 |
Q3-(2): Does the margin cancel continued BCE optimization?
No. As explained under W3, the hinge adds selective pressure below the margin without cancelling BCE. This interpretation applies to the original setting. The positive-margin cross-scene extension additionally supervises correctly signed bits that remain below its confidence target.
We sincerely thank you for your insightful and constructive suggestions. Following your suggestion, we have modified the paper, with additional visualization results in the revised paper on pages 19-22.
Reply to W1 & W2 & W3 & Q1
W1: Scene-specific adaptation versus persistent checkpoint modification.
Model-level attack identifies the modified variables as the Gaussian prediction-head parameters. We acknowledge that the original adaptation is scene-specific, and we additionally introduce extensions that retain one adapted head from the source scenes and are evaluated across unseen scenes on the same checkpoint without test-time parameter updates. We conduct the shared-head baseline, with a universal setting and a strengthened margin setting. These extensions use 64 source scenes, 8 validation scenes, and 25 unseen scenes for testing.
The shared-head baseline adapts a single shared Gaussian prediction head across the source scenes, using 150 updates per scene, and retains the final checkpoint. The Universal setting uses the same source scenes and the original watermark and fidelity objectives in Eq. (11) and Eq. (12), but trains the shared head by averaging gradients over four scenes per update. It sets every carrier-mask entry in Eq. (10) to one, so all Gaussians use the adapted head predictions without blending with the original head. The resulting checkpoint is reused unchanged on unseen scenes. Building on the Universal setting, we strengthen the existing margin term in Eq. (11). We gradually increase the confidence margin to 0.05 and give equal weight to the mean margin loss over all 48 bits and the mean over the eight largest margin violations in each rendering. This increases bit accuracy on unseen scenes from 89.17% to 93.06%, again without test-time parameter updates.
Figure 11 in Appendix B.8 shows the visual results.
W2: Independence of evaluation cameras.
We provide results in Q1-(2).
W3: The margin term and the BCE term.
Thank you for pointing out this ambiguity. The per-bit watermark loss and its derivative are:
=-\frac{1}{1+e^{s}}-\lambda\mathbf{1}[s<\kappa].$$ Only the additional hinge contribution disappears once the margin is satisfied; BCE continues to contribute. At the original default $\kappa=0$, the hinge directly penalizes negative signed logits. Correctly decoded outputs can also change through shared-head parameter updates, even when their own hinge gradient is zero. The precise interpretation is: “The margin term adds an extra penalty to bits below the target margin and stops contributing once that margin is reached, while BCE continues to promote message recovery.” Table 3 supports the empirical benefit of this combination. **Q1-(1): Which scenes and messages were evaluated?** The original evaluation uses one fixed 48-bit target message across scenes, two context views, and three target views per scene. These three target views are used for carrier construction, adaptation, and the original reported evaluation. For the two datasets, RealEstate10K consists of 7289 testing scenes, and ACID comprises 1972 testing scenes, which are the actual evaluated scene counts by following default settings. **Q1-(2): Separation between optimization and test views.** To assess camera-pose generalization, we select ten additional camera views per scene, excluded from carrier selection and training objectives. Excluding context and optimization views, each candidate is compared with the three optimization cameras using a combined score: translation normalized by the context-camera baseline plus rotation normalized by 30 degrees. We retain the lowest score and its corresponding optimization camera. After excluding scores below 0.005, we rank the remaining candidates within each scene, divide them into three equal-sized distance groups, and deterministically sample three near, three intermediate, and four far views. The quantitative results show comparable rendering quality across these groups, supporting watermark transfer to cameras excluded from adaptation and indicating relatively stable rendering quality over the evaluated held-out views. **Figure 10 in Appendix B.7** shows visual results in the revised paper. | Views | Held-out | Normalized translation | Rotation angle | Bit Acc. (%) ↑ | PSNR ↑ | SSIM ↑ | LPIPS ↓ | |---|---|---:|---:|---:|---:|---:|---:| | Source | -- | -- | -- | 99.88 | 26.20 | 0.864 | 0.137 | | Unseen | Near | 0.0403 [0.0116, 0.1251] | 0.301 [0.000, 2.037] | 94.14 | 25.95 | 0.863 | 0.140 | | Unseen | Intermediate | 0.1254 [0.0599, 0.3202] | 1.016 [0.007, 4.904] | 90.22 | 26.28 | 0.864 | 0.136 | | Unseen | Far | 0.2805 [0.1157, 0.6490] | 2.083 [0.007, 8.661] | 86.10 | 26.31 | 0.865 | 0.136 |