- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper discusses the trade-off in classifier-free guidance (CFG) between conditional alignment and sample quality/diversity, focusing on frequency-decoupled guidance (FDG). FDG suppresses low-frequency guidance to reduce oversaturation, but may discard useful structural information. The authors propose selective recovery guidance (SRG), a training-free extension of FDG that decomposes the low-frequency guidance residual into components parallel and orthogonal to the conditional low-frequency prediction, and restores only the orthogonal component (Eq. (7), Eq. (9)), gated by a normalized log-SNR window (Eq. (8)). High-frequency guidance is unchanged, and no additional denoiser forward passes are required.
Critical strengths
- Training-free and low computational overhead. SRG reuses the conditional and unconditional predictions already computed by CFG and requires no additional denoiser forward passes. This matters because the method is easy to adopt in practice and carries low deployment risk.
- Broad empirical evaluation across backbones and tasks. The paper evaluates five pretrained models, spanning class-conditional generation (EDM2-S, DiT-XL/2) and text-to-image generation (SD2.1, SDXL, SD3). This breadth supports the generality of the claimed improvements.
Critical weaknesses
- On COCO 2017, SRG ties FDG exactly or is slightly worse in FID (SD2.1/SDXL 21.96/25.68; SD3 28.31 vs. 28.10), and several Precision/Recall differences are small with no variance or significance reported; meanwhile, the SD3 DrawBench ImageReward gain from 0.695 to 0.931 is highlighted. Table 2 also contains near-zero improvements such as Parti Prompts SDXL ImageReward 0.696 to 0.697. Because an accept recommendation depends heavily on whether gains are stable rather than driven by isolated highlights, the authors need to support this with confidence intervals, multiple seeds, and per-prompt analyses across benchmarks. Otherwise, I would worry that the conclusion is setting-specific.
- The window 0.15<u_t<0.70 and η=2/3 are used uniformly across all five models, but the temporal and strength ablations are conducted mainly on SD2.1; the appendix also acknowledges that the same log-SNR interval corresponds to different numbers of effective steps across models/samplers. At the same time, the closest competing alternative FDG+APG is not evaluated, and the SD3 APG configuration is borrowed from SDXL and is not SD3-specific, which may disadvantage the baseline. For a method claimed to be training-free and general across models, this directly reduces my confidence in transferability and in the fairness of the relative comparison.
- Eq. (5) writes the recovery coefficient as A_t = A g(u_t), but the inner-product expressions mix A_t and A without clarifying that the identity holds for the product; the notation is slightly inconsistent between Eq. (5) and Eq. (9) (Sec. 4.1 vs. Sec. 4.2).
- Eq. (7) defines α_t with a denominator guard (‖C_L,t‖² > 0), but the orthogonal component ΔD^{low,⊥}_t = ΔD^{low}_t − ΔD^{low,∥}_t is stated in prose rather than as a numbered equation (Sec. 4.2), making the construction harder to verify quickly.
- Figures 1 and 2 only qualitatively illustrate oversaturation, but the paper provides no quantitative saturation or artifact metric to support the claim that orthogonal recovery alleviates oversaturation.
- The paper does not report negative results or cases where SRG underperforms FDG, which limits understanding of when the method should be preferred.
- The frequency decomposition (5×5 Gaussian filter, σ=1, factor-two downsampling, bilinear reconstruction) is specified only in Appendix B.3; there is no ablation on filter size, σ, or single-level vs. multi-level decomposition, so sensitivity to this design choice is unknown.
Questions for authors
- Please provide multi-seed variance or confidence intervals for key cells in Table 1 and Table 2, and extend the paired bootstrap analysis in Figure 5 to additional model-benchmark pairs such as SDXL DrawBench and SD3 Parti Prompts. Is the SD3 DrawBench improvement from 0.695 to 0.931 stable across all seeds and prompt slices?
- How were the window 0.15<u_t<0.70 and η=2/3 chosen, and were they validated even coarsely on SDXL, DiT, or SD3? Please report the number of effective denoiser steps inside the window for each model and sampler, so that the cross-model operational meaning of the interval is clear.
- Please unify the notation A_t and A·g(u_t) in Eq. (5) and Eq. (9), and present ΔD^{low,⊥} as a numbered equation. Also clarify the relationship between the stated bound 0≤A≤w_high−w_low and the η=4/3 ablation that exceeds it, and whether w_low+A·g(u_t)≤w_high holds under the default constraint.
- Was the SD3 APG baseline using the SDXL configuration tuned at all for SD3? If not, why not evaluate FDG+APG as a more direct selective-recovery baseline, so that APG is not underestimated due to a non-optimal configuration?
2 comments
Response to Reviewer 13Af
Dear Reviewer 13Af,
Thank you again for your careful review and helpful comments. We have addressed your concerns in our responses and supplemented the manuscript with additional comparisons and robustness analyses.
When you have a chance, we would be grateful to hear your thoughts on these updates. We hope there will be an opportunity to discuss any remaining questions and would be happy to provide further clarification.
Best regards,
The Authors
Response to Reviewer 13Af
Dear Reviewer 13Af,
Thank you for the detailed feedback. We have expanded the robustness analyses and direct comparisons and unified the mathematical notation.
W1 & Q1: Repeated sampling and uncertainty
We added SD3 Medium evaluations with three seeds per prompt on DrawBench, Parti Prompts, and HPS Prompts, including the original run (Appendix C.1/Tables 8–9). SRG achieves higher mean scores than CFG, APG, and FDG on all four metrics across all three benchmarks. Relative to FDG, mean ImageReward increases from 0.736 to 0.957, 0.982 to 1.157, and 0.990 to 1.115, respectively. These repeated evaluations support consistent improvements in alignment and learned preferences under different sampling noise.
Table 8 reports mean ± standard deviation across the three runs, showing how much the scores vary with sampling randomness. Table 9 reports 95% confidence intervals for each method's average score, estimated by bootstrap resampling prompts. The calculation details are provided in Appendix C.1.
W2 & Q2: Window and strength transfer
The default window and η=2/3 follow the timing/strength analysis on SD2.1 (Table 3). We added corresponding SD3 ablations in Appendix C.2/Table 10. Full-trajectory recovery has higher ImageReward (0.964 versus 0.931), while SRG's window yields lower FID (28.31 versus 29.06) and higher Recall (0.398 versus 0.381). Increasing η to 1 or 4/3 worsens FID/Recall and lowers ImageReward/PickScore relative to the default.
The recovery window is defined by normalized log-SNR, which describes the noise level during denoising. For each sampling schedule, we rescale its sampled log-SNR values to [0,1] and activate recovery when 0.15<ut<0.70 (Appendix A.2). The window therefore selects evaluations according to noise level; different sampling schedules can yield different active step indices and counts. The added SD3 ablations support the effectiveness of this shared window rule and moderate recovery strength beyond the original SD2.1 setting.
W2 & Q4: FDG+APG and APG configuration
We added FDG+APG to the revised main Tables 1–2, covering all five distributional model settings and all nine text-to-image model/benchmark pairs. SRG improves prompt alignment and learned preference scores over FDG+APG while retaining competitive distributional quality, supporting the benefit of selective recovery beyond combining frequency decoupling with directional filtering. Selected core results are also provided in our response to Reviewer nnEh, W1 & Q1. For SD3, APG uses the transferred SDXL parameters documented in Appendix B.4. We also evaluated APG using the SD2.1 configuration reported in the APG paper (w=10) under shared DDIM20 sampling conditions. SRG achieves higher scores on all four metrics across three benchmarks; please see Appendix D.1/Table 12 for the complete results.
W3–W4 & Q3: Unified notation and coefficient bound
We have unified the notation and component definitions in the revised equations. A denotes the recovery amplitude, while At=Ag(ut) is its gated value. For 0≤η≤1, the orthogonal low-frequency coefficient satisfies wL≤wL+At≤wH. This constrains the coefficient, not the update norm. The η=4/3 ablation deliberately tests stronger recovery beyond this range.
W5–W6: Interpretation of quality and non-improving cases
Figures 1–2 provide qualitative comparisons of saturation and artifacts, while Tables 1–2 evaluate distributional quality, alignment, and learned preferences. The fixed-state geometric property describes the added update and does not by itself quantify saturation or artifact frequency.
Our conclusion concerns improved alignment/preferences with competitive distributional quality. Table 1 also reports trade-offs: EDM2-S FID changes from 7.51 to 7.61 and Recall from 0.662 to 0.651; SD3/COCO2017 FID changes from 28.10 to 28.31. The SDXL/Parti Prompts ImageReward gain is small (0.696→0.697, Table 2). Figure 6 in the revised main paper further examines the quality–alignment trade-off across guidance settings, showing generally higher SRG scores at comparable FID in the tested range (Appendix D.2).
W7: Frequency-decomposition sensitivity
Appendix C.3/Table 11 adds SD2.1/DrawBench comparisons using 3×3, 5×5, and 7×7 kernels, Gaussian σ∈{1,1.5}, and one/two decomposition levels. SRG improves all four metrics over the corresponding FDG baseline across the tested operators. These results support recovery gains beyond the default frequency decomposition.