- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes FCFlow, which introduces defocus formation feedback into latent-space flow matching from blurry to sharp images. The method first predicts effective circle-of-confusion (CoC) radii, reblurs the predicted sharp image, and uses the residual between the reblurred image and the input to correct the latent representation. This feedback branch is used only during training. Experiments show good restoration performance on DPDD and two cross-dataset evaluations, including strong results with single-step inference.
Critical strengths
-
The motivation is clear and relevant to image restoration. By constraining the restored result through a forward imaging process, the authors attempt to address both visual sharpness and content fidelity. I find this direction meaningful.
-
The CoC branch does not require additional depth or CoC annotations. Instead, it learns through reblurring supervision using sharp images, allowing the method to use existing blurry–sharp image pairs without extra annotations.
-
The method achieves leading results under the reported evaluation settings. In addition to experiments on DPDD, the authors evaluate on LFDOF and RealDOF using a model trained only on DPDD, examining generalization across different devices and capture conditions. The reported distortion, perceptual quality, and observation consistency metrics also provide a relatively comprehensive evaluation.
Critical weaknesses
-
The discussion of Dual-Pixel and Quad-Pixel defocus deblurring methods is insufficient. Although these methods use additional input information and do not necessarily need to be included in direct performance comparisons, they are closely related to the problem studied here. I suggest discussing their connections to and differences from the proposed method in the introduction or related work. Relevant examples include Learning dual-pixel alignment for defocus deblurring, Ldp: Language-driven dual-pixel image defocus deblurring network, and Quad-Pixel Image Defocus Deblurring: A New Benchmark and Model.
-
I am not fully convinced that reblurring error can adequately reflect the fidelity of recovered details. Defocus weakens or removes high-frequency information, so sharp images containing different details may produce very similar blurry observations. The lower reblurring error in Figure 5 indicates better consistency with the observation, but it does not establish that the recovered details match the original content. Text recognition, structural matching, or controlled high-frequency perturbation experiments would help support this claim.
-
The test setting for A4 in Table 2 needs further clarification. The paper defines sharp discrepancy as the difference between the sharp ground truth and the endpoint prediction, but A4 also enables a correction based on this discrepancy during inference. It is unclear how this residual is obtained at test time. If sharp ground truth is used, this setting should be explicitly identified as an oracle comparison so that readers do not interpret it as a practical inference configuration.
-
The model uses DINOv2-L, Qwen-Image VAE, and a relatively large LightningDiT. It is therefore difficult to determine how much of the improvement comes from the proposed method and how much comes from pretraining and model capacity. The ablations with the same backbone demonstrate the benefits of individual components, but substantial resource differences remain when comparing against smaller, task-specific deblurring networks. Strong baselines with comparable pretraining and computational budgets would make the comparison more convincing.
-
The maximum CoC radius is set to 20 pixels, and the blur kernel radii follow a fixed, nonuniform sampling scheme, but the rationale for these choices is not sufficiently clear. Is a 20-pixel radius enough to cover severe defocus in the test data? How does the model handle blur beyond this range? I would like to see statistics on the blur range in the data and a sensitivity analysis of the radius limit and sampling scheme.
-
Inference on images of arbitrary resolution needs to be described more clearly. The authors explain the token grids corresponding to 512-pixel crops and the 518-pixel DINO input, but do not specify whether testing uses tiling, how overlapping regions are merged, or how positional encodings are adapted to different image sizes. These details affect boundary quality, inference speed, and the fairness of comparisons with other methods.
-
The evaluation settings in Table 1 are not sufficiently transparent. Do the baselines use official weights, or are they retrained or fine-tuned? Are the training data, iteration budgets, image resizing procedures, and metric implementations consistent? Given the relatively large PSNR improvements in some comparisons, I suggest providing reproducible evaluation configurations so that readers can assess whether the gains are obtained under comparable conditions. (Pages 7–8 and 13)
-
The dataset order and numerical results in Section 4.2 are inconsistent. The text lists DPDD, LFDOF, and RealDOF, followed by 28.74, 29.88, and 31.29 dB. According to Table 1, however, the last two values correspond to RealDOF and LFDOF, respectively. The descriptions of the corresponding improvements should also be checked to avoid confusion about the cross-dataset results. (Pages 7–8)
Questions for authors
See Weakness
4 comments
Response to Reviewer vMQH (Part 2)
W4. Contribution of model capacity and pretraining
Response. Thank you for raising this concern. To facilitate comparison across models with different capacities and pretraining, we report model complexity alongside restoration performance. All methods are profiled on the same NVIDIA RTX 4090 using inputs for latency comparison. Results are summarized below.
| Method | NFE | Params (M) | FLOPs (T) | Latency (ms) | PSNR$\uparrow$ | LPIPS$\downarrow$ |
|---|---|---|---|---|---|---|
| INIK | - | 1.977 | 0.648 | 182.24 | 26.1473 | 0.1815 |
| NRK | - | 6.094 | 0.629 | 31.28 | 26.1519 | 0.2228 |
| P2IKT | - | 3.319 | 0.688 | 47.72 | 26.3301 | 0.1920 |
| ViTDeblur | - | 121.602 | 4.057 | 621.33 | 26.0364 | 0.1993 |
| MBSD | 20 | 2529.534 | 78.732 | 4968.53 | 26.5608 | 0.1066 |
| FCFlow | 20 | 839.726 | 54.842 | 1449.10 | 29.3448 | 0.0920 |
| FCFlow | 1 | 839.726 | 5.403 | 156.84 | 28.7432 | 0.1372 |
FCFlow uses 839.726M inference-loaded parameters, including DINOv2-L, Qwen-Image VAE, and LightningDiT. At 1 NFE, FCFlow achieves 28.74 dB PSNR with a latency of 156.84 ms. At 20 NFE, it achieves 29.34 dB PSNR. Compared with MBSD at the same NFE, FCFlow uses approximately one-third of the parameters, 69.7% of the FLOPs, and 29.2% of the inference time, while achieving a 2.78 dB higher PSNR.
To isolate the contribution of our training framework, we compare Vanilla FM and FCFlow using identical backbones and pretrained components. As reported in Table 2, FCFlow improves PSNR by 3.05 dB and 1.65 dB at 1 and 20 NFE, respectively, while reducing LPIPS, demonstrating the benefits of formation-aware training.
W5. CoC radius limit and kernel-bank sampling
Response. Thank you for raising these concerns. We conducted additional experiments on DPDD to investigate the radius sampling strategy and the 20-pixel upper bound. All configurations use 10 sampled radii. The results in Table 7 of the revised manuscript are reproduced below.
| Variant | Sampling | PSNR | LPIPS | |
|---|---|---|---|---|
| A | 16 px | Non-uniform | 28.6127 | 0.1398 |
| B (Ours) | 20 px | Non-uniform | 28.7432 | 0.1372 |
| C | 30 px | Non-uniform | 28.7356 | 0.1375 |
| D | 20 px | Uniform | 28.6549 | 0.1390 |
With , non-uniform sampling outperforms uniform sampling, supporting denser sampling in the small-radius regime. Increasing from 16 to 20 pixels improves restoration, whereas extending it to 30 pixels brings no further benefit.
To characterize the effective blur-radius distribution, we analyzed 2,660 non-overlapping DPDD blocks, selecting the disk radius that minimizes the RGB MAE between the reblurred sharp reference and observed blurred input. As shown in Fig. 8 of Appendix A.3, 91.20% of the blocks have best-fit radii within 20 pixels, while 8.80% exceed this range, including 4.25% reaching 30 pixels. Fig. 9 shows a representative region where the MAE is minimized at 20 pixels and increases for larger radii. These results support as a practical upper bound covering most, but not all regions. For regions exceeding this limit, the formation renderer provides only an approximation of the observed blur.
W6. Arbitrary-resolution inference
Response. Thank you for this suggestion. We have added detailed descriptions of the arbitrary-resolution inference procedure in Appendix A.4 (lines 885–902), including tiling, overlap fusion, and positional encoding.
Briefly, inference is performed at the original image resolution using tiles with a 64-pixel overlap and 448-pixel stride. Boundary tiles are shifted to ensure full image coverage, and overlapping latent tiles are merged using normalized separable Hann weights before VAE decoding. Positional encodings are applied independently within each tile using fixed token grids ( for DINOv2 and for LightningDiT), without image-wide positional rescaling.
W7. Baseline weights and evaluation reproducibility
Response. Thank you for this comment. As clarified in Sec. 4.2 (lines 366–367), all baseline methods use their officially released pretrained checkpoints, without additional retraining or fine-tuning. Their training data and iteration budgets follow the respective official configurations. All methods are evaluated using the same test splits, image preprocessing settings, and metric implementations, as detailed in Appendix A.2.
W8. Dataset ordering and numerical inconsistency in Section 4.2
Response. We thank the reviewer for pointing out this inconsistency. The dataset ordering and corresponding numerical results have been corrected throughout the revised manuscript.
Thank you for the authors' response. The rebuttal has addressed most of my concerns, and I will revise my score accordingly.
We sincerely thank the reviewer for their follow-up and for acknowledging that our response addressed most of their concerns. We greatly appreciate their constructive feedback, which has helped us improve the paper.
Response to Reviewer vMQH (Part 1)
Thank you very much for taking the time to read our paper and for providing valuable feedback. We hope that our responses below adequately address your concerns and questions.
W1. Coverage of Dual-Pixel and Quad-Pixel methods
Response. Thank you for the suggestion. We have revised Sec. 2.1 (Single-Image Defocus Deblurring, p. 3, lines 129-136) to include discussions of DPANet [1], LDP [2], and QPDD/LMNet [3]. The revised discussion clarifies that these methods exploit dual-pixel or quad-pixel sub-aperture observations, whereas FCFlow operates on a conventional single RGB image. We further highlight the connection to LDP: both methods model spatially varying defocus, but LDP uses a blur map derived from dual-pixel observations to guide restoration, while FCFlow estimates an effective CoC map from a single RGB image and leverages differentiable reblurring feedback to enforce formation consistency during training. Accordingly, our quantitative comparisons follow the single-RGB-image input setting.
References
W2. Reblurring consistency and fidelity of recovered details
Response. Thank you for this important observation. We agree that lower reblurring error does not necessarily imply faithful detail recovery, as different sharp structures may produce similar blurred observations. Reblurring with the effective defocus forward model guides Flow Matching toward physically consistent restorations, while formation-consistent feedback helps align the recovered details with the original content. To address this concern, we have added a reference-based structural fidelity evaluation in Sec. 4.4, including quantitative boundary evaluation (Table 6) and visual comparisons (Fig. 6).
Specifically, using the existing checkpoints, we compared Vanilla FM (A0) and FCFlow (A7) at 1 NFE on all DPDD test pairs using Canny boundary matching with a 1-pixel tolerance. As shown below, FCFlow consistently improves boundary precision, recall, and mean Boundary F1 over Vanilla FM.
Fig. 6 further illustrates the improved boundary correspondence. These results provide complementary evidence of improved structural fidelity beyond reblurring consistency.
W3. Test-time sharp discrepancy in A4
Response. Thank you for pointing out this ambiguity. We clarify that A4 is an oracle ablation: its inference-time residual is computed using the paired sharp ground truth S and the decoded endpoint prediction S(t), i.e., RA4=S−S(t). Since the sharp ground truth is unavailable in practical inference, A4 serves only as an oracle diagnostic rather than a deployable configuration. We have explicitly labeled A4 as an oracle correction in Table 2 (line 406) and clarified the residual definition in the “Test-time correction and inference NFE” paragraph of Sec. 4.3 (lines 482–483).