- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes structure anchored conditional response steering, it’s a training free human video generation approach. The method separates semantic and structural response and experiments show improvement over existing guidance methods.
Critical strengths
- The paper is well written and well motivated, and it is tackling an important limitation in conventional CFG.
- The method is effective and it’s used during inference time without requiring additional training cost.
Critical weaknesses
- The proposed method seems to be a combination of a couple existing guidance approaches, which might limit its novelty.
- There’s insufficient ablation studies and it is difficult to evaluate the effectiveness of different components.
- The proposed conditional differences based on semantic and structural factors are not necessarily disentangled, and removing structural conditions can also change semantic predictions, and replacing text may influence pose or appearance. It might need additional justification for semantic structural decomposition.
Questions for authors
Could the authors clarify the novelty of the proposed method relative to existing guidance approaches, provide more comprehensive component-wise ablations, and justify whether the semantic and structural conditional responses are sufficiently disentangled to support the proposed decomposition?
Response to Reviewer XwsG (3/3)
W3. Disentanglement of the two responses. We agree that the two responses are not exactly disentangled: the network is nonlinear, so removing the structure can shift semantic content and changing the text can affect pose or appearance. Sec. 2.2 states that "axis-wise" refers only to selective intervention on different conditioning sources and does not assume orthogonality or independence. Each response is evaluated at the same state xt and changes one condition while holding the others fixed. The method is designed for this cross-talk rather than relying on its absence. The ablations show it directly: applying semantic steering uniformly (w/o AT) leaves CLIP almost unchanged (29.11 vs. 29.20) but degrades MPJPE and identity, i.e., the semantic response does leak into structure and appearance. Localizing it with AT, bounding its angle relative to the anchor, and renormalizing the output to ∥vB∥ limits this leakage. Conversely, removing the structural term changes CLIP by only 0.04, so the structural response does not noticeably alter semantics.
We hope these responses address the reviewer's concerns, and we would be grateful if the reviewer could consider updating the score. We are happy to clarify any further questions.