- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes CleanVideo, a concept erasure method for text-to-video diffusion models. It uses low-dimensional subspace intervention with a tri-modal gating mechanism. The gating module combines visual features, timestep information, and text semantics to adjust the intervention strength. Meanwhile, the method uses surrogate concepts and preservation loss to reduce the influence on unrelated content. Experiments on nudity, artistic styles, and object erasure show that the method outperforms several baseline methods on three video generation models.
Critical strengths
- The proposed tri-modal gating mechanism considers spatial and temporal changes during video generation. It provides a reasonable way to adjust concept erasure at different regions and denoising steps.
- The experiments cover three erasure tasks and three video generation models. The results on multi-concept erasure and concept-recovery attacks are also useful.
Critical weaknesses
- Theorem A.4 uses a low-rank argument based on cross-attention, but it does not clearly explain why concept directions from different samples share the same low-dimensional subspace. Meanwhile, Eq. (3) uses a fixed orthonormal basis R, but its construction and relation to the target concept are not clearly explained.
- In Appendix E.11, removing a branch means replacing its output with a constant 0.5 after sigmoid. However, this also changes the scale of the final gate. The paper also lacks comparisons with simpler gating methods. Therefore, it is unclear whether the improvement comes from the three signals or the proposed fusion mechanism.
- The artistic style evaluation uses GPT-4o to classify the generated images into five artist styles. However, the evaluation prompt does not include a "none of the above" option. Even if the target style is successfully removed, the image must still be classified as one of these styles. This may affect the reliability of the style erasure results.
Questions for authors
Please see the weaknesses above. I am willing to reconsider my rating if these concerns are properly addressed.
4 comments
Follow-up to Reviewer MZTP
Dear Reviewer MZTP, we would appreciate your feedback on our clarifications and new experiments. Do they address your concerns, or is there anything we can clarify further? Thank you.
My concerns have been largely addressed. I threfore decide to raise to raise my score.
Thanks to Reviewer MZTP
Thanks for your raising and reply! ! !
Response to Reviewer MZTP
Thank you for the detailed feedback. We address your three concerns below.
W1. Construction of R and the cross-sample argument
R is initialized with orthogonal directions and kept fixed. Orthogonality avoids redundant directions in the limited update space. R determines where representations can change; target–surrogate pairs train A, b, and the gates to remove the target concept, while preservation examples constrain changes to benign content. Different samples share R, but receive different updates depending on their visual features, timestep, and text.
Sharing a subspace does not require identical concept directions across samples. In Appendix A, we now state the shared low-rank assumption explicitly: when the collected concept directions admit a low-rank approximation, their leading singular directions capture most of the total energy. The revised bound applies to the sample collection. This motivates low-dimensional intervention; the implemented R is fixed rather than constructed from these singular directions, and its use is learned through target–surrogate supervision.
W2. Gate strength and simpler alternatives
We added controls that replace each branch with a learnable constant vector. This lets the control learn its strength without using that branch’s input. We also tested fully constant gating and additive fusion. For additive fusion, all three branches are retained, with
g=σ((zvis+ztime+ztext)/3).
All variants use the same training data and other training and evaluation settings on HunyuanVideo nudity erasure.
Default intervention strength: 1.0. Leakage is a percentage; quality scores use a 0–100 scale.
We then varied inference strength without retraining:
At the same 6.0% leakage, the full model exceeds additive fusion by 1.4–2.0 points on all four preservation metrics. Thus, its advantage extends beyond a difference in intervention strength. These results are included in Appendix E.11, Tables 22–23.
W3. Forced-choice style evaluation
We added “none of the above” to the GPT-4o classifier and re-evaluated the same videos, keeping frame sampling and other settings unchanged. This option counts as no target-style detection on target prompts, but not as correct style preservation on non-target prompts.
Each cell below reports target-style detection ↓ / unrelated-style preservation ↑ (%), averaged over five artists.
CleanVideo retains the lowest target-style detection and highest unrelated-style preservation among the erasure methods on all three backbones. The results are included in Appendix E.7, Table 17; the original five-option results remain available for comparison.