- Rating
- 2
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper proposes a new method to solve imaging inverse problems using a pretrained flow matching model (unspecific to the considered inverse problem). The method is build on FLOWER, which itself was built on PNP-FLOW. Both FLOWER and PNP-FLOW iterations consist of 1) a data consistency step; 2) a renoising step unsing random noise; 3) a flow-based denoising step. Usually in the renoising step 2, one draws independent noise samples and then averages over them.
Contributions:
- The main modification with respect to FLOWER that is proposed in this paper is to use antithetic noise (ie and , where ). This helps to improve the image restoration, as the experiments show.
- The second modification with respect to FLOWER is the ``Posterior velocity correction'' but I am not even sure it is really different than what is done in FLOWER or if it's a different way to write it.
Overall assesment The paper is well written and easy to follow, and the numerical results are reasonably competitive. However, I find the contribution limited (little methodological novelty, not much theoretical understanding of why such a method would solve a MAP problem / do posterior sampling). There have been so many papers over the last two years trying to slightly improve the state of the art for inverse problems. While this is certainly a valuable objective, I believe the inverse problem community would benefit more from studies that try to understand what these solvers actually do and what guarantees they provide.
Critical strengths
- Using antithetic noise improves the restoration performance at a fixed NFE compared to FLOWER, which is one of the state-of-the-art methods
- The use of antithetic noise is justified
- The paper is clear
Critical weaknesses
- Lack of novelty compared to FLOWER
- Visually, the results are not so impressive: the method seems to suffer from the same kind of oversmoothing than it's predecessors
- Comparison to recent diffusion baselines are missing (see below) and it would be good to evaluate on another dataset than Celeba and AFHQ-Cat that are very centered on a face.
Questions for authors
-
How does the velocity correction step you propose lead to a different ``denoising'' update than the one of FLOWER? Could you also please provide numerical results of your method but without the antithetic noise (say just one random sample) and compare it to FLOWER-1 (with refinement) so that we see the effect of the velocity correction.
-
Since the antithetic noise reduces the variance, can you observe a reduced variability between runs compared to FLOWER? Is this desirable?
-
Do you have an insight on why the reconstructions are oversmoothed visually?
-
Since it has clearly been established that flow matching and diffusion both build a path of denoiser for noise levels , it would be necessary to also compare to the SOTA methods that were proposed in the diffusion framework (using the same networks as for flow matching). Could you compare your method to DAPS [1]?
-
Why do you use flows trained with OT couplings? What does it bring to your method?
[1] Zhang, B., Chu, W., Berner, J., Meng, C., Anandkumar, A., & Song, Y. Improving diffusion inverse problem solving with decoupled noise annealing. CVPR 2025
14 comments
Response to Reviewer xMu8 (2/4)
Summary. […] I am not even sure it is really different than what is done in FLOWER or if it's a different way to write it.
Q1. How does the velocity correction step you propose lead to a different "denoising" update than the one of FLOWER? Could you also please provide numerical results of your method but without the antithetic noise (say just one random sample) and compare it to FLOWER-1 (with refinement) so that we see the effect of the velocity correction.
No, velocity correction is not Flower written in another way. It gives a different update. In the "denoising" step, velocity correction keeps the network prediction and adds a shift along the measurement residual (Eq. 11). This shift is computed from the measurement, not the network, so it needs no extra network call. Combined with the proximal step, this scales Flower's update by . Proposition 1 gives the resulting step:
Flower is the case . On each observed mode it moves only a fraction of the way toward . It never crosses the measurement, so the next network call pulls the iterate back toward the prior. PPC-Flow uses under , so every residual mode still contracts. For example, on SR×2 at , Flower moves 83% of the way to , while PPC-Flow moves 183% and the next pull-back lands near . Fig. 5 confirms this on SR×2: at , velocity correction lowers the endpoint error on the observed pixels by a quarter. Here is not a free knob. It grows only in the late steps, where the pull-back dominates, and a prior-free cap keeps every residual mode contracting for any network (Proposition 1).
Here is the single-trajectory comparison you asked for, without pairing and at the same NFEs. Both columns keep Flower's refinement step, so the gain shows the effect of velocity correction alone. The PSNR values in dB come from Table 14:
| Task | Flower-1, with refinement () | Ours, , no pairing () | Gain |
|---|---|---|---|
| SR×2 | 32.346 | 33.081 | +0.735 |
| Random inpainting | 33.123 | 33.629 | +0.506 |
The gain stays positive on the other three tasks as well (Appendix D.5). On SR×2, one corrected trajectory is already on par with Flower-5, which averages five. Interestingly, most of the MSE drop lies on unobserved pixels, 84% on SR×2 and all of it on random inpainting (Table 4). The correction anchors the observed pixels, and the network then does a better job on the missing ones.
Could a larger do the same? No. Since for any , rescaling never crosses the measurement. We checked this by scaling with constant factors from to , with velocity correction off and . Table R5 in Appendix D.5 gives the PSNR gain in dB:
| Task | Best rescaling | PPC-Flow |
|---|---|---|
| SR×2 | +0.38 | +0.81 |
| Random inpainting | +0.01 | +0.67 |
| Box inpainting | 0 | +0.15 |
| Denoising | 0 | +0.12 |
| Deblurring | 0 | +0.05 |
The best factor stays well below velocity correction on every task, so no setting of Flower's reproduces it. Our related work section already draws this distinction: Flower's refinement fades near the terminal time, exactly where it matters. To make this distinction clearer, we revised Section 3.2 to state it explicitly right before Proposition 1, and Appendix D.5 now gives the full -rescaling control and the single-trajectory results.
Response to Reviewer xMu8 (3/4)
Overall. […] not much theoretical understanding of why such a method would solve a MAP problem / do posterior sampling […]
Q3. Do you have an insight on why the reconstructions are oversmoothed visually?
Q2. […] can you observe a reduced variability between runs compared to FLOWER? Is this desirable?
These three questions share one answer, so we group them. With , the network predicts the conditional mean , and the proximal step takes the mean of a local Gaussian posterior, as Theorem 1 shows. These annealed solvers are therefore best seen as approximate minimum-MSE (posterior-mean) estimators, not global MAP solvers. With , they draw local conjugate posterior samples instead (Proposition 4). We now state this in Section 2.2 and Appendix D.2. Beyond this single-step view, the paper gives three trajectory-level results. Lemma 2 shows that early corrections fade through per-step contractions. Proposition 1 shows that the capped update contracts every observed residual mode for any prior. And Proposition 2 gives an exact variance identity that predicts the pairing gain with no free parameter.
Smoothness. This is a deliberate choice, not a side effect. PPC-Flow sits on the fidelity side of the perception–distortion trade-off (Blau & Michaeli, CVPR 2018). It targets the minimum-MSE estimate, so it does not invent details that the measurement cannot determine. Many inverse problems, such as MRI and microscopy, need exactly this, because hallucinated details are not acceptable there (Bhadra et al., IEEE TMI 2021, and Belthangady & Royer, Nature Methods 2019). That said, within this regime PPC-Flow still keeps more high-frequency detail than Flower-5. On all five tasks it retains more high-frequency energy and has a lower high-frequency error (Appendix D.2). When sharp textures matter more than fidelity, the mode of Appendix A.5 can be used, and velocity correction helps there as well.
Variability. Yes, it drops a lot. With fewer network calls than Flower-5, PPC-Flow has less than half of its run-to-run variance, and less than a tenth of that of Flower-1 (Tables 15 and 16). For a point estimate, this is desirable: the variance is part of the MSE, so lowering it raises PSNR and makes repeated runs agree. No uncertainty information is lost either. Pairing keeps each trajectory's marginal unchanged (Section 3.3), and with the spread across runs is not a calibrated posterior uncertainty in the first place. Flower makes the same observation in its Appendix 8.5.3: "led Flower to generate samples concentrated in higher-probability regions, while failing to capture the tails of the posterior". For uncertainty quantification, the mode is the right tool.
Response to Reviewer xMu8 (1/4)
Thank you for the careful review and the direct questions. We agree that the community needs to understand what these solvers actually compute, and we tried to make that the center of our answers. New material in the revised PDF is shown in blue.
Flower is an excellent solver and a natural starting point for us, and PPC-Flow keeps its proximal step. Our contribution is a deeper look at what happens along the trajectory, which gives a definite answer to a question Flower leaves open. In its Appendix 8.5.4, Flower reports that averaging more trajectories saturates after about five runs. Our analysis explains why, and shows how the NFE budget should be spent instead. The analysis applies to any flow solver that alternates a network prediction, a proximal data step, and noise re-injection, such as PnP-Flow and Flower. It reveals three behaviors:
Each mechanism targets one of these behaviors. Velocity correction over-relaxes the late data step to undo the pull-back, and a prior-free cap keeps every residual mode contracting (Proposition 1). On SR×2 it cuts the shared error by 15%, which no rescaling of the proximal weight can do, as we show in Post 2/4. Antithetic pairing flips the sign of the re-injected noise, where the variance actually comes from, and cancels its linear part with a single pair. After one pair, the variance is below 2% of the MSE (Table 16).
In short, the analysis turns "average more trajectories" into "make each trajectory better". With only two trajectories, PPC-Flow beats Flower at the same budget, at five times the budget, and even at its averaging ceiling, on all five CelebA tasks. Here is Table R1 from Appendix D.1, with PSNR in dB:
We estimate the ceiling by running Flower with five antithetic pairs, which is already very close to the limit of infinitely many runs.