- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The paper introduces FGTC, a training-free correction for multi-step diffusion-based super-resolution. It selects an early low-frequency prediction according to structural similarity with the upsampled LR input and uses recent prediction history as the high-frequency reference. Subsequent predictions are blended with these references using deviation-dependent weights, then re-encoded for the original sampler. Experiments on StableSR and SeeSR across three datasets show consistent improvements in PSNR, with perceptual improvements in most settings. The paper makes a modest contribution to super-resolution. However, the comparisons with relevant state-of-the-art methods are insufficient to establish its incremental value, and I find the overall novelty limited.
Critical strengths
-
The paper addresses a practical problem: improving reconstruction fidelity without retraining a diffusion backbone or requiring GT at inference. Using different temporal references for structure and detail is an intuitive design, and FGTC is demonstrated on two existing models.
-
The reported gains over the original backbones are consistent. Table 1 shows PSNR improvements of 0.92-1.31 dB across all six backbone/dataset combinations. StableSR also improves LPIPS and DISTS on all three datasets, and the visual examples illustrate cleaner boundaries and reduced spurious textures.
-
The ablations help assess the method beyond its overall performance. Table 3 compares all four early/history reference assignments, while Table 4 separates the proposed correction from decode-encode and wavelet round trips. In particular, decode-encode alone improves PSNR by about 0.18 dB on SeeSR/DRealSR, compared with about 1.07 dB for full FGTC. This supports a contribution from the correction itself.
Critical weaknesses
-
My main reservation concerns the incremental contribution relative to StructSR, which is discussed in the related work but not included in the experiments. StructSR already selects an early prediction using structural similarity to the LR input and uses that prediction to guide subsequent restoration without additional training. FGTC differs by selecting the reference in the low-frequency band, using recent history for high frequencies, and adapting correction strength to reference deviations. These are meaningful distinctions to investigate, but comparisons with unmodified backbones do not establish how much they add over the existing structural-reference approach. A matched comparison with StructSR would be more informative for assessing the contribution than further comparisons with general-purpose SR models. The absence of this comparison does not imply that FGTC would perform worse; it leaves the size and nature of the advance unresolved.
-
The internal ablations support the design, although they do not replace that external comparison. On SeeSR/DRealSR, Table 3 reports PSNR of 27.82 for the proposed Early/History assignment versus 27.70 for Early/Early, together with improvements in SSIM, LPIPS, and DISTS. This suggests a benefit from the high-frequency history branch. Its consistency across images or sampling seeds would help judge the strength of this particular contribution. Importantly, the Early/Early variant is an FGTC ablation, not an implementation of StructSR. MASF is also relevant because it aggregates predictions by frequency; a short account of the differences, and an adapted comparison if feasible, would further clarify FGTC's position.
-
The practical trade-off deserves a clearer account. For SeeSR on DIV2K-Val, PSNR improves from 22.36 to 23.38, while LPIPS changes from 0.3194 to 0.3321 and DISTS from 0.1968 to 0.2111. This is an exception to otherwise broadly positive results, rather than evidence by itself that FGTC over-smooths images. Discussing representative cases would help explain when the correction preserves useful detail and when it may trade perceptual similarity for fidelity. Runtime is also not reported, despite the additional decoding and encoding during sampling, so the cost of the gains is difficult to assess.
Questions for authors
-
Could the authors compare FGTC with StructSR using the same backbone, sampler, step count, and evaluation protocol? A focused experiment on the existing SeeSR/DRealSR setting would already help. Please also explain the differences in reference selection and how the selected reference enters the sampling update.
-
How consistent is the Early/History improvement over Early/Early across test images or sampling seeds? A paired summary on the existing evaluation would help establish the contribution of using recent high-frequency history.
-
For the Table 5 analysis, which images and timesteps are used? Could the authors clarify whether the reference preference remains within comparable sampling stages? Shared temporal trends are a possible alternative explanation for part of the association, rather than an established problem with the analysis.
-
What are the runtime and peak memory at matched sampling settings, and what kinds of images account for the SeeSR/DIV2K-Val perceptual-metric degradation?
4 comments
Response to Reviewer V2Na (part 2)
Reply to Q3: Reference preference at different sampling stages
The analysis in Table 5 uses 93 DRealSR images and decoded clean predictions along their StableSR sampling trajectories, with GT used to compute reconstruction errors. We exclude the initial snapshot. Both Early and History references are evaluated on the same steps, –, with steps – used to initialize the history buffer with .
The preference for temporal references in each frequency band remains consistent both after timestep control and within comparable sampling stages: Early for LL and History for HF. Using the original analysis settings, we calculated partial Spearman correlations for each image by removing the effect of timestep ranks from the ranks of reference deviations and reconstruction errors measured against GT, then correlating the residuals. The table compares these correlations with the original results as mean ± standard deviation across images. Higher means are bold.
| Frequency | Metric | Early reference | Recent history |
|---|---|---|---|
| LL | Spearman ρ | 0.796 ± 0.260 | 0.206 ± 0.240 |
| LL | Partial Spearman ρ | 0.742 ± 0.201 | 0.167 ± 0.367 |
| LL | High-error AUC | 0.820 ± 0.256 | 0.717 ± 0.223 |
| HF | Spearman ρ | 0.776 ± 0.291 | 0.825 ± 0.198 |
| HF | Partial Spearman ρ | 0.623 ± 0.235 | 0.726 ± 0.207 |
| HF | High-error AUC | 0.909 ± 0.179 | 0.943 ± 0.093 |
To further check whether the preference holds within comparable sampling stages, we compare Early and History (Hist.) on the same 93 images and the same steps, dividing – into three stages of 65 steps each: early (–), middle (–), and late (–). We calculate ordinary Spearman correlations for each image within each stage, then average across images. Early has a higher LL correlation and History has a higher HF correlation in all three stages. The second table reports the mean correlations for each stage, with the higher mean for each frequency band in bold.
| Sampling Stage | Reference | LL Spearman ρ | HF Spearman ρ |
|---|---|---|---|
| Early (194–130) | Early | 0.6021 | 0.2934 |
| Early (194–130) | Hist. | -0.0134 | 0.6401 |
| Middle (129–65) | Early | 0.7148 | 0.7388 |
| Middle (129–65) | Hist. | 0.1695 | 0.7612 |
| Late (64–0) | Early | 0.8242 | 0.8022 |
| Late (64–0) | Hist. | 0.5061 | 0.9098 |
Response to Reviewer V2Na (part 3)
Reply to W3 & Q4: Image quality, runtime, and peak memory
The perceptual tradeoff on SeeSR/DIV2K-Val is closely related to the recoverability of fine structures under synthetic degradation. On DIV2K-Val, severe degradation can obscure fine lines and densely repeated structures. SeeSR uses semantic guidance and pretrained diffusion priors to generate realistic details, but insufficient structural information in the LR input may lead to local structural distortions and textures inconsistent with GT. FGTC corrects these deviations using a selected early LL reference and recent HF prediction history. For severely degraded, densely structured regions, improving structural fidelity may also change the appearance of fine lines and local texture contrast, resulting in higher reconstruction accuracy at some perceptual cost. This tradeoff is specific to SeeSR/DIV2K-Val: FGTC improves both LPIPS and DISTS with SeeSR on RealSR and DRealSR, as well as with StableSR on DIV2K-Val. The two backbones also differ in their training datasets (LSDIR and FFHQ10K for SeeSR versus DF2K and OST for StableSR), which may contribute to their different perceptual responses.
To further illustrate this tradeoff across different image contents, we provide two representative examples in Section 4.3 (Figure 5 and Table 3) of the revised manuscript. For the building facade, severe degradation obscures the densely repeated window grids, making their geometry difficult to recover. FGTC brings these structures closer to GT, improving structural fidelity, while changes in the appearance of fine lines come at a certain perceptual cost. In contrast, the stained glass window retains relatively clear main contours. FGTC preserves these structures while removing textures inconsistent with GT, improving all five metrics. These examples demonstrate that FGTC can simultaneously improve fidelity and perceptual similarity when the main structures remain sufficiently recoverable. When severe degradation blurs densely repeated structures, FGTC can improve their alignment with GT, while changes in fine-line appearance may incur a certain perceptual cost. The table below reports all five metrics for these two examples, with PSNR in dB and the better result for each image in bold.
| Image | Method | PSNR ↑ | SSIM ↑ | MS-SSIM ↑ | LPIPS ↓ | DISTS ↓ |
|---|---|---|---|---|---|---|
| 0821_pch_00015 | SeeSR | 19.35 | 0.5321 | 0.8907 | 0.2396 | 0.2480 |
| 0821_pch_00015 | SeeSR+FGTC | 20.24 | 0.6587 | 0.9192 | 0.1763 | 0.2120 |
| 0845_pch_00025 | SeeSR | 14.98 | 0.4082 | 0.7152 | 0.2172 | 0.1957 |
| 0845_pch_00025 | SeeSR+FGTC | 16.29 | 0.4797 | 0.7601 | 0.2577 | 0.2217 |
Runtime and peak memory.
To compare FGTC's inference cost with the original models and StructSR, we measured runtime and peak GPU memory on SeeSR and StableSR under the same settings for each backbone. All tests use an NVIDIA GeForce RTX 3090 for 4× super-resolution with 512×512 outputs. StableSR uses 200 sampling steps and SeeSR uses 50.
FGTC introduces no trainable parameters and keeps the original sampling step count. Its extra runtime over the original models comes from reference computation, decoding, encoding the predictions again, and frequency correction during sampling. The table below reports runtime and peak GPU memory. Lower is better for both measures.
| Backbone | Method | Peak GPU memory (GiB) ↓ | Runtime (s/image) ↓ |
|---|---|---|---|
| SeeSR | Baseline | 6.7153 | 7.32 |
| SeeSR | +StructSR | 6.7153 | 14.84 |
| SeeSR | +FGTC (Ours) | 6.7203 | 11.77 |
| StableSR | Baseline | 7.0746 | 19.53 |
| StableSR | +StructSR | 7.1120 | 41.78 |
| StableSR | +FGTC (Ours) | 7.1120 | 30.07 |
Updated Manuscript and Summary of Revisions
Dear Reviewer V2Na,
Thank you again for your detailed review and suggestions. We have uploaded a revised manuscript incorporating the following additions:
- Direct quantitative and visual comparisons with StructSR are provided in Section 4.2, Table 2 and Figure 5.
- Paired PSNR results across images in Appendix B.2, Table 10.
- Analysis settings, results after timestep control, and comparisons within sampling stages in Appendix A, Tables 7 and 8.
- Representative cases showing detail preservation and the perceptual tradeoff in Section 4.3, Figure 6 and Table 3.
- Runtime and peak GPU memory measurements in Appendix D, Table 11.
All changes are marked in blue. We hope this additional evidence and our responses address your concerns and support a more positive assessment of our work. We would appreciate your feedback and would be happy to answer any remaining questions.
Best regards,
The Authors
Response to Reviewer V2Na (part 1)
Thank you for your detailed review and suggestions. We hope our responses address your questions and concerns. We also hope the added comparisons and analyses support a more positive assessment of our work.
Reply to W1, W2 & Q1: Comparison with StructSR
To compare FGTC with StructSR, we ran quantitative tests with SeeSR and StableSR on DRealSR, RealSR, and DIV2K-Val, using the same backbone and sampling budget for each comparison. The results show that FGTC achieves better reconstruction fidelity in all six settings and also improves perceptual metrics in most settings. The table below includes the original models and both added methods, with the best results in each group in bold.
Reply to Q2: PSNR improvements across images
With the selected early LL reference unchanged, we compared Early/History with Early/Early using SeeSR on 93 DRealSR images. PSNR improves on 89 images (95.70%), and the 95% confidence interval for the mean paired gain is above zero, as estimated by paired image bootstrapping. These results show that recent HF prediction history benefits most images.