- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies concept erasure for native text-to-3D generative models. The authors argue that existing closed-form concept editing methods, originally developed for 2D diffusion models, overlook the multi-stage nature of native 3D generation, where geometry and appearance are produced by different stages. Based on this observation, the paper formulates concept erasure as a stage-aware editing problem and introduces STAGE, a training-free closed-form editor.
Critical strengths
- The motivation is clear and specific to native 3D generation. In TRELLIS, the structural and appearance stages play different roles, so applying the same edit indiscriminately across the pipeline may either fail to remove the target concept or introduce unnecessary collateral changes.
- The stage-locality claim is supported by direct experiments. The results directly support the central claim that different concept types depend on different stages of the native 3D generation pipeline.
Critical weaknesses
- Since the core stage-aware argument is closely tied to TRELLIS's explicit structural/appearance decomposition, it is unclear how well the proposed formulation generalizes to other native 3D generators with different architectures or representations. A second backbone, even with a smaller-scale evaluation, would substantially strengthen the generality of the claim.
- The quantitative comparison focuses mainly on UCE and OCE, both of which are closed-form editors originally developed for 2D generation. Adding a 3D baseline for comparison would be more convincing
- The preservation component is mainly computed using the remaining concepts within the same five-class semantic axis (as shwon in Table 4). For example, when erasing one object concept, preservation is evaluated primarily on the other object categories in that axis. This is useful, but it does not fully establish that the edited model preserves its general behavior on a broad distribution of unrelated prompts. A larger retain benchmark covering diverse categories and compositional prompts would provide stronger evidence against collateral degradation.
- The current stage assignment relies on predefined concept categories, rather than being automatically inferred by the model or data. It is still unclear how to determine which generation stage should be edited when the concept to be erased involves geometry, appearance, material, or object identity simultaneously.
Questions for authors
Same as weakness
5 comments
Thank you for the detailed response and additional experiments. Most of my concerns have been adequately addressed. I have one remaining question regarding W4: Since Mode-SL achieves comparable or better performance across all three axes, what are the advantages of concept-dependent stage assignment over universally applying Mode-SL, particularly in terms of preservation and efficiency?
Response on concept-dependent stage assignment
We thank the reviewer for the follow-up. Mode-SL is a suitable default when the concept type is unknown. When the type is known, the concept-dependent assignment gives better preservation at nearly the same cost.
Preservation
Results of STAGE on TRELLIS. The last column is the fraction of assets whose attribute outside the edited axis keeps its top-1 label (material by CLIP / MINC-23 after shape edits, shape by CLIP after material edits).
| Axis | Mode | F | P | 3D-US | Other attribute kept |
|---|---|---|---|---|---|
| Shape | Mode-S (assigned) | 0.70 | 0.91 | 77.7 | 0.68 / 0.66 |
| Shape | Mode-SL | 0.71 | 0.89 | 77.2 | 0.67 / 0.66 |
| Material | Mode-L (assigned) | 0.45 | 0.92 | 56.4 | 0.92 |
| Material | Mode-SL | 0.72 | 0.83 | 72.9 | 0.76 |
The object axis is assigned Mode-SL, so the two settings coincide there. On shapes, Mode-SL adds no 3D-US over Mode-S and lowers preservation. On materials, it raises forgetting at the cost of preservation, on the other concepts of the axis and on the shape of the edited assets. Mode-L also leaves the weights of the structural stage unchanged, so the same seed gives the same voxel support.
All three editors preserve the other concepts of the axis better under the assigned mode. Preservation P:
| Axis | Editor | Assigned mode | Mode-SL |
|---|---|---|---|
| Shape | STAGE | 0.91 | 0.89 |
| Shape | UCE | 0.85 | 0.81 |
| Shape | OCE | 0.67 | 0.45 |
| Material | STAGE | 0.92 | 0.83 |
| Material | UCE | 0.84 | 0.71 |
| Material | OCE | 0.74 | 0.35 |
P is higher under the assigned mode in 29 of the 30 pairs of editor and shape or material concept.
Efficiency
The two options have nearly the same cost. Both use one closed-form solve and add no cost at generation time, and the assigned mode folds the correction into 28 cross-attention layers instead of 56. The advantage of the assigned mode is preservation.
Choice of mode
The assigned mode is the choice when the concept type is known and preserving the rest of the model matters most. Mode-SL is the choice when the type is unknown or when forgetting matters most. STAGE has the highest 3D-US of the three editors under both options, on every axis.
In the revised paper, the mode comparison is in Section 4 (paragraph "Mode Assignment and Stage Locality", Table 2), and the cross-attribute evaluation is in Appendix F (Table 14).
We thank the reviewer for the review and for noting that the stage-locality claim is supported by direct experiments. We address the concerns below.
W1: Second backbone
We ran the full benchmark on a second generator, DiffSplat [1], which repurposes Stable Diffusion 1.5 to generate 3D Gaussian splats as multi-view splat images. Its architecture and representation differ from those of TRELLIS. All three editors use the same concepts, prompts, seeds, evaluators, and hyperparameters as on TRELLIS. 3D-US on DiffSplat (higher is better):
STAGE has the highest 3D-US on every axis and overall, with a margin of 13.7 points over the strongest baseline (13.5 on TRELLIS).
In the revised paper, this is in Section 4 (paragraph "Generalization to a Second Generator", Table 3a), with per-concept results in Appendix J (Table 18) and the generated assets in Appendix L.
W2: A 3D baseline
We are not aware of an erasure method for native text-to-3D generators. The only prior 3D unlearning method [2] fine-tunes the 2D multi-view diffusion model at the front of an image-to-3D pipeline, and has no counterpart in a native generator whose stages read the text. We therefore adapted the strongest closed-form editors, UCE [3] and OCE [4], under identical conditions: the same prompts and seeds, the same stages and layers, and the same one-at-a-time hyperparameter sweep, with each method at its best configuration. 3D-US on TRELLIS:
STAGE also scores highest of the three editors under every edit mode that erases a concept (table in W4).
In the revised paper, the absence of a native 3D baseline is stated in Section 2 (second paragraph), and the adaptation of the baselines is in Appendix B.
W3: Preservation on a broad retain set
We added a retain set of 60 held-out TRELLIS-500K captions. They are not in the caption sample used for K_0, and they name none of the 15 concepts or their synonyms. They describe objects, characters, and scenes from many categories, each with several attributes, for example "Rusty container with blue lid window and a red triangle.". Each caption is generated with the same seed before and after every one of the 15 edits of Table 1, for every editor.
STAGE preserves unrelated prompts at the level of UCE and above OCE, while forgetting the target concepts more than both.
In the revised paper, this is in Section 4 (paragraph "Preservation on Unrelated Prompts", Table 3e), with results per axis in Appendix I (Table 17).
W4: Stage assignment for concepts that combine several attributes
The per-axis assignment follows the architectural role of each stage and is tested directly by the mode crossover. 3D-US on TRELLIS:
For a concept that combines geometry, appearance, material, and identity, or whose type is unknown, Mode-SL edits every stage that reads the text and requires no inference about the concept type. Applied to all three axes, Mode-SL gives STAGE an overall 3D-US of 72.5, compared with 49.6 for OCE and 52.1 for UCE.
In the revised paper, this is in Section 4 (paragraph "Mode Assignment and Stage Locality", Table 2).
References
[1] Lin, Chenguo, et al. "DiffSplat: Repurposing image diffusion models for scalable Gaussian splat generation." ICLR'2025.
[2] Wang, Shixuan, et al. "Machine unlearning in 3D generation: A perspective-coherent acceleration framework." NeurIPS'2025.
[3] Gandikota, Rohit, et al. "Unified concept editing in diffusion models." WACV'2024.
[4] Sun, Yuhao, et al. "Orthogonal concept erasure for diffusion models." arXiv'2026.