- Rating
- 3(+1)
- Confidence
- 4
- Informativeness
- 3
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes SNaP, a one-step posterior sampling method for linear inverse problems. The authors derive a measurement-aware Gaussian noise distribution for linear forward operators. The mean is chosen as the optimal estimate that minimizes MSE with the ground truth image; the covariance is chosen such that uncertainty is suppressed in well-measured directions while remaining large in weakly measured and null-space directions. A conditional MeanFlow is then trained on (clean image, measurement) pairs, using the measurement-aware Gaussian as the noise prior rather than a standard Gaussian.
Extensive experiments show strong performance on image reconstruction tasks (inpainting, super-resolution, deblurring) across the CelebA and AFHQ-Cat datasets, as well as multi-coil fastMRI evaluation. SNaP outperforms/is competitive with many diffusion/flow baselines at only 1 NFE. Ablations help validate specific design choices such as the source distribution.
Critical strengths
1. The problem is timely and well-motivated. Enabling one-step generation for posterior sampling is novel and potentially practically useful. Empirical results across distinct benchmarks are convincing: SNaP shows strong performance at only 1 NFE. The image reconstruction calibration results, combined with the synthetic Gaussian mixture experiment, are evidence that SNaP captures the full posterior distribution well.
2. The idea of a measurement-aware noise prior that suppresses uncertainty in the well-defined directions, but encourages uncertainty in the poorly measured directions, under the linear operator is interesting and novel to my understanding. The authors do extensive theoretical analysis that justifies most of the methodological design choices.
Critical weaknesses
1. The method requires training a new conditional MeanFlow model for each forward operator, which is precisely the limitation that training-free methods like DPS avoid. This is understandable because the method trades off training time to retain one-step inference, which training-free methods lack, so I don't view this as a fatal weakness. But I believe that this still weakens the practical utility of the method.
2. The experiments don't include comparison against relevant consistency-based inverse problem solvers [1,2,3], nor are they discussed in the related work. These are important baselines because they also focus on using one/few-step generative models for inverse problems.
Questions for authors
-
(Major Weakness 1) It's understandable that SNaP requires forward operator-specific training. But I'd like to see a demonstration of generalizability across the forward operator family: i.e., how does SNaP performs on box inpainting if it trains on a distribution of box masks, then is evaluated on a held-out evaluation distribution of masks? I believe that demonstration of such a generalization capability would significantly improve the method's practical utility.
-
(Major Weakness 2) The main experiments are missing a comparison against another one/few-step inverse solver. Can at least one of [1–3] be evaluated on an image reconstruction or MRI benchmark to enable a fair comparison with SNaP? Such a baseline would help determine whether SNaP’s 1-NFE performance is compelling relative to other methods specifically designed for low-NFE inverse solving. The discussion and appendix comparisons with NullFlow and VFM are appreciated, but both don't appear as baselines in the main image reconstruction/MRI experiments. The related-work section should also discuss [1–3].
-
(moderate Weakness 3) How do other simple choices of affect SNaP performance? How robust is SNaP to this design choice? Since the method derivation works for general , this is an important design choice that should be studied more in depth.
-
(clarification) What does SNaP stand for?
Author response has satisfied my concerns. Raising score from 2 to 3.
[1] M. Gülle, J. Yun, Y. U. Alçalar, and M. Akçakaya. “PnP-CM: Consistency Models as Plug-and-Play Priors for Inverse Problems.”
[2] T. Garber and T. Tirer. “Zero-Shot Image Restoration Using Few-Step Guidance of Consistency Models (and Beyond).”
[3] J. Zhao, B. Song, and L. Shen. “CoSIGN: Few-Step Guidance of ConSIstency Model to Solve General Inverse Problems.”
4 comments
(moderate Weakness 3) How do other simple choices of affect SNaP performance? How robust is SNaP to this design choice? Since the method derivation works for general , this is an important design choice that should be studied more in depth.
Prompted by the reviewer's comment, we train SNaP with sources built from several working covariances .
SNaP is robust to the choice of at a fixed mean variance. Across the covariances tested, PSNR varies by at most 0.25 dB and Δcal stays within [0.90, 1.03].
Besides , we test two classes of working priors, all with the same mean variance (CelebA deblurring).
- Per-pixel diagonal, with entries drawn uniformly at random.
- Colored, stationary covariances with power-law spectra , normalized so that every pixel has variance .
| PSNR M=1 | PSNR M=16 | LPIPS M=1 | Δcal (→1) | |
|---|---|---|---|---|
| (paper) | 32.94 | 35.69 | 0.019 | 1.03 |
| Per-pixel diagonal, | 32.95 | 35.50 | 0.018 | 0.90 |
| Per-pixel diagonal, | 32.97 | 35.63 | 0.018 | 0.96 |
| Colored, α = 1.5, ω₀ = 2 | 32.73 | 35.45 | 0.020 | 0.96 |
| Colored, α = 0.5, ω₀ = 10 | 32.90 | 35.70 | 0.019 | 1.01 |
We have revised the paper to include this study in App. B.6 (Table 15).
Q1. What SNaP stands for.
SNaP stands for (S)ampling for (N)oisy inverse (P)roblems.
Thanks for the response. The new results have answered my concerns; I'm increasing my score from 2 to 3.
Thank you for considering our response and raising your score. If any concerns are still affecting your assessment, we’d be happy to address them.
We thank the reviewer for the feedback. We address each point with new experiments: we train one model on a family of box masks and test it on unseen mask sizes (W1), compare SNaP with PnP-CM on CelebA and fastMRI and with PnP-CM and CM4IR on CelebA-HQ (W2), and evaluate four additional working covariances C (W3). See our point-by-point responses below.
Prompted by the reviewer's comment, we trained SNaP on CelebA box inpainting with a randomly placed 40×40 box for each training image. The method needs no change, since the source is built in closed form from whatever mask is given.
One model trained on the mask family generalizes to unseen box sizes, gaining 5.9–6.9 dB over the fixed-mask model with a single draw.
We test on 100 images with new random boxes at the training size and at two sizes never seen in training, and score the submitted fixed-mask model on the same masks (PSNR at M = 1 / M = 4).
The family-trained model is lower only on the centred mask the submitted model was trained for, by about 1.5 dB.
We have revised the paper to include this experiment in App. B.3 (Table 9). The Limitations now state that a new type of operator still needs a new model.
We compare SNaP with PnP-CM [1] and CM4IR [2] in two settings, and discuss [1–3] in the related work.
At matched 4 NFEs, SNaP outperforms PnP-CM on every metric in both settings and CM4IR on every metric except SR ×4 PSNR, where CM4IR is 0.37 dB higher. In our setting, even a single SNaP draw achieves higher PSNR than PnP-CM at 4 NFEs in seven of eight tasks.
1. PnP-CM adapted to our setting. We distill consistency models on our CelebA and fastMRI training splits and run PnP-CM at 4 NFE with our operators.
At matched 4 NFEs, SNaP achieves higher PSNR and better perceptual or structural metrics across all eight tasks. Even at 1 NFE, SNaP achieves higher PSNR in seven of eight tasks.
2. SNaP adapted to PnP-CM's setting. To keep the comparison fair to PnP-CM, we train SNaP on its operators and training-set size, and run PnP-CM and CM4IR with PnP-CM's released CelebA-HQ 256 checkpoint, σy=0.05 and 300 test images (our rerun reproduces PnP-CM's paper within 0.15 dB). PSNR / LPIPS-VGG.
At matched 4 NFEs, SNaP achieves the best performance on five of six metrics, with the sole exception of SR ×4 PSNR, where CM4IR is 0.37 dB higher.
We have revised the paper to include these results (Tables 1 and 3, App. B.2) and a discussion of the related works [1–3] (Sec. 5).