- Rating
- 2(+1)
- Confidence
- 2(−1)
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This paper characterizes the minimax risk of estimating the noise level (or rather its precision ) from noisy images corrupted by additive white Gaussian noise. Two theorems are given depending on which assumptions are made on , the signal law (low intrinsic dimensionality or strong log-concavity). This paper is exclusively theoretical.
Critical strengths
The paper is mathematically well-founded, although I did not check all the proofs in Appendix. The literature review is well conducted.
Critical weaknesses
I recommend rejecting this paper because it is entirely theoretical and its conclusions are unlikely to provide any practical value to the research community.
Major:
-
The paper is exclusively theoretical. Its goal is only to give minimax rates under two different assumptions on the signal distribution. The conclusion is that "the difficulty of blind noise estimation is governed by the structure of the signal law", which is an obvious conclusion to me. It is hard to envision any application for this paper. I do not think it will be useful to the community.
-
The authors motivate their work in the context of blind denoising in diffusion models where blind denoising can improve image generation quality despite the missing noise input. However, not a single example or concrete application is given with diffusion models.
Minor:
-
The notation on line 199 initially confused me. Indeed, in machine learning, and particularly in the denoising literature, it is quite common to use the subscript of the expectation to indicate the random variables with respect to which the expectation is taken. Here however following the traditional minimax estimation framework, I understand that is a parameter rather than a random variable. I suggest clarifying this point to avoid any potential confusion for the reader.
-
Please number each of your equations.
-
Some references about single-image noise estimation are missing [a, b].
[a] Alessandro Foi, Mejdi Trimeche, Vladimir Katkovnik, and Karen Egiazarian. Practical Poissonian-Gaussian noise modeling and fitting for single-image raw-data. IEEE TIP, 2008.
[b] Stanislav Pyatykh, Jurgen Hesser, and Lei Zheng. Image noise level estimation by principal component analysis. IEEE TIP, 2013.
Questions for authors
In line 199, I have the intuition that
so that reads . Indeed, the more the strength of the noise is and the more difficult it will be to estimate the noise level. Do you agree with me?
3 comments
I thank the authors for their response. In particular, I find the toy example in Q5 interesting and recommend adding it to the paper.
My initial inclination was to reject the paper, as I was skeptical that its conclusions would offer any practical value to the community. However, after carefully considering the authors' responses and the comments from the other reviewers, I have decided to slightly increase my overall rating. At the same time, I have lowered my confidence in my assessment, given my limited expertise in minimax estimation.
We thank the reviewer for reconsidering our responses. The Gaussian example discussed in Q5 has been added to Section 2.2 (Equation 13) of the revised manuscript.
Response to Reviewer r3to
We thank the reviewer for carefully reading our paper and for the useful suggestions, particularly on practical relevance, presentation, and related literature. We address the concerns below.
Q1. Novelty and theoretical significance. Our contribution goes beyond the qualitative observation that signal structure matters. We characterize the optimal quantitative dependence of noise-estimation risk on signal structure.
Under low intrinsic dimensionality, the k2/d2 term can dominate the usual 1/d rate. Our lower-bound construction uses the same known P at two noise levels, showing that latent signal variation can conceal a precision change of order k/d. The MLE matches the lower bound up to logarithmic factors.
Under strong log-concavity, the centered norm estimator attains the minimax rate
\min\left\\{\Delta_\Lambda^2,\frac{(1+\alpha^{-1})^2}{d}\right\\},
with sharp dependence on α for fixed Λ. This identifies a different estimation mechanism based on concentrated signal energy rather than low-dimensional support.
We will emphasize these quantitative insights and the same-P construction in Sections 1.1 and 4.2.
Q2. Practical relevance and diffusion models. We appreciate the concern about experimental validation. Kadkhodaie et al. (2026) already provide extensive experiments demonstrating successful blind denoising in diffusion models. Their analysis relates this success to concentration of the posterior over the missing noise level, which allows blind and noise-conditioned denoisers to be close.
Our paper complements these experiments by showing that the corresponding low-dimensional noise-estimation rate is minimax optimal up to logarithmic factors. We aim to explain the statistical mechanism underlying blind denoising, rather than propose another practical algorithm. Our optimality result concerns noise estimation; it does not establish a lower bound on denoising or diffusion-sampling error.
We will clarify this connection in Sections 1.1 and 2.1 and explain the scope of our conclusions in Section 5.
Q3. Notation and presentation. We agree that the expectation notation could be clearer. The subscript in Eλ,P specifies the observation law, with λ treated as a fixed unknown parameter:
Eλ,P[(λP(Y)−λ)2]=∫(λP(y)−λ)2pλ(y),dy.
The estimator may use P, and the supremum over λ∈Λ gives the worst-case risk. We will clarify this notation in Section 2.2 and number the displayed equations throughout the paper.
Q4. Missing references. We thank the reviewer for pointing out these references. We will incorporate both into the paper and clarify their relationship to our work.
All three works study noise estimation from a single noisy observation by exploiting signal structure. Foi et al. (2008) fit a signal-dependent Poissonian--Gaussian noise model to raw images, accounting for effects such as clipping. Pyatykh et al. (2013) estimate additive Gaussian noise using PCA of image patches, exploiting low-variance directions to distinguish noise from image content.
The difference lies in the goal and statistical setting. These papers develop practical image-based estimators, whereas we assume a known signal law P and characterize minimax estimation risk under explicit structural assumptions. Our work provides a complementary theoretical account of how signal structure affects noise-estimation difficulty.
We will add both references to Section 1.2 and discuss their similarities to our work, as well as the differences in noise models, assumptions, and theoretical goals.
Q5. Dependence on noise strength. We appreciate this question. The dependence on noise strength depends on the parameterization and loss. We estimate precision λ=σ−2, so stronger noise corresponds to smaller λ.
For P=δ0, let a=λ−1 and consider
a=d∣Y∣2,λ=∣Y∣2d−2.
For d>4, their exact mean-squared errors are
E(a−a)2=d2a2,E(λ−λ)2=d−42λ2.
Thus, stronger noise increases absolute variance-estimation error but decreases absolute precision-estimation error in this example. Both relative errors remain of order 1/d. In particular, the worst-case precision risk need not occur at λmin.
Our minimax formulation uses squared precision loss over a fixed interval Λ. Rate equivalence with standard-deviation estimation involves Λ-dependent constants and does not imply identical pointwise dependence on noise strength.
We will clarify the parameterization and add this Gaussian example in Section 2.2.