- Rating
- 3
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes a new diffusion-based inverse-problem solver, termed FANO, built on an annealing framework. Its key insight is to optimize the injected noise at each annealing step, rather than directly optimizing or . To exploit the inherent prior on the noise norm, the authors introduce a chi-square-based regularization term into the optimization objective, constraining the optimized noise from deviating too far from the typical Gaussian shell. The performance of FANO is evaluated on FFHQ and ImageNet.
Critical strengths
I find the identified phenomenon of radial drift interesting and useful. This observation provides a convincing explanation for why SITCOM may deviate from the manifold, and makes the core motivation of the paper particularly clear. I also find the idea of optimizing the injected noise, rather than directly optimizing or , to provide a meaningful insight for diffusion-based inverse problems. In addition, the proposed norm prior and the resulting optimization procedure appear well motivated, though there are some questions about the weight as discussed below.
Critical weaknesses
-
Please at least place the title and author information at the top of the first page.
-
I noticed that the weight used in the paper is generally very small, and is even set to zero for two tasks. This makes me question how much the proposed norm prior actually contributes to the performance. Only for random inpainting do the authors use , where the prior appears to play a meaningful role. However, in most other cases, the weight is below . From Figure C.1, I also observe that generally achieves reasonably good performance, while increasing can even lead to performance degradation on some tasks. Therefore, I find it difficult to assess how necessary it is to constrain the optimized noise to remain near the typical Gaussian shell, or whether optimizing the noise itself is already sufficient to achieve substantial improvements.
-
Although the authors appear to have selected several recent methods as baselines, I would like to see comparisons with other representative approaches. For example, DDNM (NFE=100) is a simple yet effective inverse-problem solver, and a comparison in terms of both reconstruction quality and computational efficiency would be valuable. Since the paper uses a pixel-space diffusion model, DDNM should be directly applicable to at least the linear inverse problems considered here. In addition, some more recent methods, such as [1], also consider the noise distribution from a related perspective. Comparing against such methods would help better position FANO within the existing literature.
I also find the comparison with INO somewhat unusual, as INO appears to focus on settings with imperfect generative priors, such as those arising from shortened sampling trajectories, which are not the primary settings considered in this paper.
-
Several recent studies have also recognized the importance of accounting for the noise prior at each step of diffusion-based inverse-problem solving, such as [2]. A more detailed discussion of these works, or additional experimental comparisons where applicable, would help clarify the novelty and contribution of FANO relative to existing approaches.
[1] Plug-and-Play Diffusion Meets ADMM: Dual-Variable Coupling for Robust Medical Image Reconstruction. ICML, 2026.
[2] Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior. ICLR, 2026.
Questions for authors
I am curious about what Theorem 1 is intended to establish. In particular, part (ii) appears to state that the objective value at a non-optimal point is necessarily larger than the optimal value, which seems rather straightforward.
I understand the authors' argument that if the optimal noise corresponds to a radius , forcibly projecting it onto the unit sphere may lead to suboptimal loss value. However, I feel that this observation and the motivation for imposing a Gaussian prior are somewhat conflict. Directly optimizing the measurement-consistency objective can naturally drive the noise away from the Gaussian prior, which is precisely the issue underlying the radial drift observed in SITCOM. This motivates introducing a Gaussian prior to regularize the optimization.
On the other hand, a high-dimensional Gaussian distribution is inherently concentrated near a thin spherical shell. For typical image dimensions (e.g., ), approximating the radial distribution with a spherical-shell constraint seems quite reasonable to me. This brings me back to my earlier concern: why does the method already achieve strong performance when is close to zero? I would appreciate a more thorough discussion of the actual contribution and necessity of the proposed norm prior, particularly in distinguishing its effect from the benefit of optimizing the noise itself.
7 comments
Response to Reviewer 81MF (2/5)
W2. is small in general and zero for two tasks: does the improvement come from the norm prior or from optimizing the noise itself?
As you suspect, the improvement comes mainly from optimizing in the noise coordinate, which is the core design of FANO. FANO-Euc with , which only changes the search variable, is already 1.15 dB (HDR) and 1.12 dB (nonlinear deblurring) better than SITCOM (Appendix C.3). The norm prior handles the radial deviation that remains in the noise coordinate, and it does have an effect: without it, the radius on the two linear deblurring tasks shrinks to 0.83 and 0.88 in the late layers, and on HDR it expands to 1.22 at the final layer; with the prior it returns to about 1 and to 1.07, respectively. The effect shows mainly in perceptual quality: LPIPS improves on almost every image for Gaussian deblurring and on nearly 90% of the images for motion deblurring, while PSNR changes by at most 0.14 dB. The table separates the two parts: going from FANO-Euc () to FANO () adds only the polar decomposition, and going on to FANO (default ) adds the prior.
| Gaussian | Motion | Random | PR | HDR | NL | |
|---|---|---|---|---|---|---|
| FANO-Euc () | 30.64 / 0.225 | 33.03 / 0.167 | 33.99 / 0.122 | 32.54 / 0.172 | 29.18 / 0.171 | 30.80 / 0.182 |
| FANO () | 30.76 / 0.234 | 33.15 / 0.172 | 34.02 / 0.120 | 32.12 / 0.188 | 29.76 / 0.159 | 30.85 / 0.184 |
| FANO (default ) | 30.65 / 0.225 | 33.04 / 0.167 | 34.07 / 0.120 | 31.98 / 0.187 | 29.88 / 0.157 | 30.83 / 0.183 |
A small value of does not mean that the prior is weak. Writing the injected noise as a radius and a direction (), the negative log-density of the standard Gaussian prior in these coordinates is . The negative log-posterior at layer is
while FANO's per-layer objective is
Multiplying the first expression by gives the second with , which is 0.005 at . In the main table, for Gaussian deblurring, motion deblurring, phase retrieval, HDR, and nonlinear deblurring lies in 0.0015–0.01, exactly this order of magnitude. The potential is also multiplied by , so a small numerical value of does not mean a weak prior.
As for the three tasks with equal to 0 or 1 that you mention, box inpainting uses 0 and random inpainting uses 1. On both inpainting tasks the radius barely moves, so the value of hardly matters (over the whole sweep in Appendix C.2, the PSNR of random inpainting changes by only 0.05 dB). For SR, was selected by PSNR and is therefore 0; with , LPIPS improves on all 30 images of the sweep while PSNR drops by 0.06–0.09 dB.
In the revision, the ablation table above is in Appendix C.2 (Table 8, lines 1081–1085).
Response to Reviewer 81MF (3/5)
W3. DDNM (quality and efficiency); comparison with DC-PnPDP; is the comparison with INO appropriate?
We added DDNM as suggested, and FANO has higher PSNR in seven of the eight comparisons. DC-PnPDP targets medical image reconstruction, and we discuss it in the related work; INO is the existing method closest to FANO.
We use DDNM+ (100 steps), the variant for noisy measurements, with 100 images per dataset and the same measurements as Table 1. DDNM has higher PSNR only on ImageNet box inpainting; in LPIPS, DDNM is lower on SR (both datasets) and on FFHQ box inpainting. In efficiency, DDNM is 8 to 28 times faster, but it relies on an SVD of the operator and cannot be applied to motion deblurring (whose kernel uses reflective boundaries) or to the three nonlinear tasks. Quality and runtime:
| SR ×4 | Gaussian | Box | Random | |
|---|---|---|---|---|
| DDNM, FFHQ | 30.37 / 0.203 | 28.92 / 0.229 | 23.89 / 0.141 | 31.12 / 0.167 |
| FANO, FFHQ | 30.68 / 0.232 | 30.65 / 0.225 | 25.33 / 0.156 | 34.07 / 0.120 |
| DDNM, ImageNet | 26.81 / 0.304 | 25.89 / 0.341 | 20.62 / 0.212 | 27.26 / 0.240 |
| FANO, ImageNet | 27.03 / 0.321 | 27.01 / 0.317 | 20.40 / 0.206 | 29.94 / 0.157 |
| Time per image (s): DDNM / FANO | 4.0 / 80 | 3.4 / 94 | 3.2 / 27 | 3.2 / 36 |
As you note, DC-PnPDP also looks at the distribution of the noise, but at a different property. It recovers the dual variable in a PnP diffusion + ADMM framework to remove the steady-state bias and turns the structured residual in the denoiser input into approximately white noise; it is concerned with whether the noise spectrum is white, whereas we are concerned with the noise norm. It targets linear CT and MRI reconstruction with medical images and dedicated priors, a setting that differs from our natural-image evaluation, so we did not compare with it experimentally and discuss it in the related work instead.
Regarding INO, you are right that its starting point is imperfect generative priors. We still compare with it because it is the existing method closest to FANO: it also optimizes in the noise space and uses a shell constraint. We use its recommended configuration.
In the revision, the DDNM results are in Appendix E.4 (new, Table 19, lines 1478–1487), and Section 2.4 adds the discussion of DC-PnPDP (lines 200–202).
W4. Recent work such as DMAP also accounts for the noise prior at each step
Thank you for pointing out DMAP (Xu et al., ICLR 2025). It starts from an idea similar to FANO's, namely that the noise norm should be taken into account at every step. The difference is that DMAP uses a hard projection, whereas FANO uses the noise as the search variable and keeps a soft radial degree of freedom; in addition, DMAP guides each reverse step, whereas FANO uses annealed decoupling.
In each reverse step, DMAP runs several gradient-descent steps on and, after each step, projects onto the sphere of radius centered at the transition mean; the paper also proposes training a lightweight conditional score estimator. FANO instead re-noises from the anchor at each layer and searches in the noise coordinate.
You suggest experimental comparisons where applicable. The public implementation of DMAP is built on Stable Diffusion 2 (a latent model) and cannot load the pixel-space models we use; porting it would require rewriting its latent-space derivation and interfaces, so we did not compare with it directly. Instead, we added the same kind of hard shell projection to SITCOM (projection after every update) and tested it on HDR and nonlinear deblurring, where radial drift is pronounced. It reaches 28.26 on HDR and 29.75 on nonlinear deblurring, 0.23 and 0.07 dB above SITCOM without the projection (Appendix D.1) and 1.6 and 1.1 dB below FANO. Fixing the radius at 1 in the noise coordinate (FANO-Sphere) is also 0.82 dB below FANO on HDR. A hard constraint therefore helps less than changing the search variable and adding a soft constraint.
In the revision, Section 2.2 introduces DMAP (lines 139–140) and Section 2.4 contrasts it with FANO (lines 198–200), and the results of SITCOM with a hard shell projection are in Appendix C.3 (new, lines 1124–1130 and Table 10).
Response to Reviewer 81MF (1/5)
Thank you for the positive assessment and the specific questions. Your main question is how much the norm prior contributes, given that λrad is generally very small (W2, Q2). You also suggested additional baselines such as DDNM and a discussion of recent work such as DMAP, and asked what Theorem 1 (Proposition 1 in our submission) is meant to establish (W3, W4, Q1). The revision is uploaded; our point-by-point replies follow.
Unless stated otherwise, results are on 100 FFHQ images with measurement noise σy=0.05 and are reported as PSNR / LPIPS. Changes in the revision are marked in blue, and each reply ends with the location of the changes, including line numbers.
The main new results are:
W1. Title and author information at the top of the first page
Done as requested. In the submission, the teaser figure floated above the title on the first page; in the revision, the title and author information are at the top of the first page.