- Rating
- 2
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
Summary
This paper proposes LARC, a late-stage reconstruction corrector for diffusion-based inverse problems. It preserves the early sampling trajectory of an existing solver and replaces subsequent updates with a two-stage procedure: measurement-guided initialization, which balances data fidelity with proximity to the denoised prediction and current sampling state, followed by preconditioned score refinement at a fixed noise level. The preconditioner adjusts updates according to the measurement operator’s geometry. Experiments on FFHQ and ImageNet cover inpainting, super-resolution, and deblurring, demonstrating improvements in reconstruction accuracy across four host solvers. Component and scheduling ablations further support the framework’s practical effectiveness. However, its technical novelty and the specific limitation it addresses remain insufficiently established relative to existing PnP and score-based correction methods. Moreover, the compatibility between the residual statistics after initialization and the original noise level used for subsequent score updates requires further clarification.
Critical strengths
Strengths
-
Consistent improvements in reconstruction accuracy. The experiments demonstrate PSNR improvements across multiple inverse problems on FFHQ and ImageNet.
-
Flexible integration with existing solvers. LARC reuses pretrained diffusion models without additional training and is evaluated with four different solvers.
-
Informative component and schedule ablations. The paper examines initialization, preconditioning, inner iteration counts, and correction placement. In particular, the comparison against isotropic updates with matched average scaling and the placement experiments under fixed NFE budgets provide useful evidence for the effectiveness of the proposed design choices.
Critical weaknesses
Weaknesses
-
Limited technical novelty. The main components are closely related to existing methods. Adapting updates across directions according to the measurement operator’s spectral structure is already reflected in DDRM [1], while SNIPS [2] employs curvature-based preconditioned score updates. Score correction at a fixed noise level is related to existing predictor–corrector approaches [3], and the measurement-guided initialization resembles the data-consistency subproblems in PnP methods such as DiffPIR [4]. Although the specific updates differ and I acknowledge the reported performance improvements, the contribution appears primarily to be a combination of these established ideas applied during late-stage sampling. The paper does not sufficiently clarify the substantive technical novelty of this combination.
-
The distinct contribution remains unclear. Despite the performance improvements, the paper does not sufficiently explain which limitations of existing solvers the proposed design choices address or what independent benefits they provide. The ablations support the effectiveness of initialization and preconditioning, but the necessity of the additional current-state constraint in Eq. (10) lacks targeted justification. Consequently, it remains unclear what generalizable methodological insight the paper provides beyond an effective combination of existing techniques.
-
The consistency between initialization and subsequent score updates requires clarification. The initialization in Eq. (10) may alter both the magnitude and statistical structure of the reconstruction residual, which is not guaranteed to follow the Gaussian perturbation model associated with noise level . Nevertheless, the second stage continues to use the score network conditioned on the original noise level . Previous studies have shown that a mismatch between optimization-induced residuals and the input distribution of pretrained denoisers can degrade denoising performance or introduce artifacts [5, 6]. The authors should therefore explain why retaining the original noise level is appropriate and whether this potential mismatch introduces additional reconstruction error. The theoretical analysis assumes an exact score and does not address this practical concern, while targeted discussion or empirical validation is also missing.
References
[1] Kawar et al. Denoising Diffusion Restoration Models. 2022.
[2] Kawar et al. SNIPS: Solving Noisy Inverse Problems Stochastically. 2021.
[3] Song et al. Score-Based Generative Modeling through Stochastic Differential Equations. 2021.
[4] Zhu et al. Denoising Diffusion Models for Plug-and-Play Image Restoration. 2023.
[5] Shrestha and Fu. Taming Score-Based Denoisers in ADMM: A Convergent Plug-and-Play Framework. 2026.
[6] Du et al. Plug-and-Play Diffusion Meets ADMM: Dual-Variable Coupling for Robust Medical Image Reconstruction. 2026.
Questions for authors
Questions
-
The initialization in Eq. (10) may alter the magnitude and statistical structure of the reconstruction residual. Could the authors explain why it remains appropriate to use the score network conditioned on the original noise level ? Could this potential distribution mismatch compromise the reliability of the updates or introduce additional reconstruction error?
-
What specific limitation of existing diffusion-based inverse solvers does LARC aim to address? Compared with existing data-consistency corrections, preconditioned updates, and score refinement methods, what is LARC’s central distinguishing contribution? Could the authors clarify how its specific design choices address this limitation?
7 comments
Response to Reviewer B58Y (2/3): limitation, design rule and the current-state term (W2/Q2)
Notation. For an eigenvector of with eigenvalue : , , (the share of direction fixed by the measurement), () and .
W2/Q2. Limitation addressed, design rule and the current-state term.
- Limitation. Late in sampling the measurement has little left to give: once data consistency holds, the remaining error lies in directions the measurement does not determine (all of it, for noiseless measurements), and only the prior can reduce it. Existing solvers spend one network evaluation per level on this (DDRM, ΠGDM, DiffPIR, DPS) or run costly inner loops at every level (DAPS, SITCOM: 10–25× DiffPIR's runtime in Table 1). Giving the host the same or a larger late budget on its own schedule is worse than LARC in all 12 settings (Table R1, reply to Reviewer 1jHd).
- Design rule (the transferable insight). At each late noise level, spend several network evaluations on the prior, and let one energy around the host state decide both where to start and how far each direction may move. Per eigendirection, the minimizer of Eq. (10) is and has eigenvalue : each direction is taken from the data by the share and refined by the prior in proportion to the remaining share . The rule uses only the host's state and noise level, so the same rule applies to all four hosts.
- Independent benefits (Table 3; PSNR gain over using neither, inpainting / SR / motion). Start alone: +1.79 / +0.08 / +2.58 dB. Metric alone: +1.32 / +0.22 / −2.58 dB. Both: +4.24 / +0.40 / +2.96 dB. Start and metric work together: without the Eq. (10) start, hurts motion deblurring (24.81 vs. 27.39 dB with isotropic steps); with it, is best (30.35 vs. 29.97 dB).
The current-state term of Eq. (10). is a posterior mean, while is the state the host has committed to. The term has two effects. (i) It moves the start in weakly observed directions from toward by the share , which keeps the correction local to the host trajectory and gives the first score evaluation a noisier input (see W3, part 3). (ii) It rescales the trust in the data and the step: LARC equals the variant without the term whose anchor is and whose and are divided by . Table R7 measures both. On the noiseless tasks, rows 2 and 3 coincide and give effect (i) alone; on motion deblurring they also change the trust in the noisy data.
Table R7. ΔPSNR (dB) relative to LARC; inpainting / SR 4× / motion. Row 1 is relative to the Table 1 run; rows 2 and 3 are paired with a LARC run from their own batch (same measurements, seeds and host prefix). Row 2: the term is removed and the step is divided by ( unchanged). Row 3: only the start is computed without the term; the refinement steps are unchanged.
| Variant | LARC(DiffPIR) | LARC(DAPS) |
|---|---|---|
| Term removed, all else fixed | −0.06 / −2.52 / −4.90 | −0.42 / −2.69 / −9.77 |
| Term removed, step compensated | −0.03 / −0.03 / −1.59 | −0.08 / −2.79 / −1.90 |
| Term removed from the start only | −0.03 / −0.03 / −0.36 | −0.08 / −2.79 / +0.12 |
- Step scale. Compensating the step recovers the SR loss with DiffPIR (−2.52 → −0.03 dB) and most of the motion losses (−4.90 → −1.59 dB, −9.77 → −1.90 dB).
- Anchor, effect (i). On the noiseless tasks it accounts for the whole 2.79 dB on SR with DAPS and for at most 0.08 dB in the other three settings.
- Motion deblurring. With the step compensated, removing the term still costs 1.59 dB (DiffPIR) and 1.90 dB (DAPS), where the term also sets the trust in the noisy data; removing it from the start alone changes PSNR by −0.36 dB and +0.12 dB.
Response to Reviewer B58Y (3/3): noise level of the inner score evaluations (W3/Q1)
W3/Q1. Noise level of the inner score evaluations.
- Why level t. Stage 2 is descent on , the prior smoothed at the host's level, so plays the role of a regularization strength, as the denoiser level does in PnP. For the exact MMSE denoiser, Tweedie's identity holds at every , not only at level- samples, and is the proximal map of an implicit penalty whose Moreau envelope is up to a constant (Gribonval, 2011; Gribonval & Nikolova, 2020). Level is also the level of in Eq. (10) and of the transition (17)–(18) that follows.
- How far the inner inputs are from level-t samples. In directions the measurement fixes, Stage 1 replaces the host's perturbation by data; there the weight of vanishes in the noiseless case, so those score components are not applied. In unobserved directions the first input keeps the share of the host's level- noise (1/3, 0.55 and 2/3 for inpainting, SR and motion with DiffPIR; times this share in partly observed directions), and the following steps reduce it. The current-state term is what keeps this share: without it, the first input carries none of the host's noise in these directions (effect (i) in part 2).
- The mismatch studied in [5, 6]. [5, 6] study this mismatch for PnP iterates fed to a diffusion denoiser. It is most severe with ADMM, whose dual variable accumulates structured residuals: in [5] it "further distorts" the noise geometry, and [6] finds the shift "milder" without such a memory variable (its spectral homogenization adds +0.15 dB to PnP-HQS). [5] corrects the mismatch with the AC-DC denoiser, [6] with spectral homogenization. LARC has no dual variable and takes at most 8 steps per level. Eqs. (17)–(18) then move the corrected estimate to the next level with DiffPIR's transition: the new perturbation combines fresh noise (a fraction ζ of its variance; all of it when ζ = 1, e.g. LARC(DiffPIR) on inpainting) with , the rescaled difference between the current state and the corrected estimate. The next level restarts from the minimizer of its own .
- Net effect. From the same state and with no more NFE than the host's own continuation, LARC ends above it in all 12 settings (Table R1), by +0.19 / +0.71 / +1.15 dB for DiffPIR: whatever mismatch remains does not outweigh the correction.
The revision adds the comparison with [1–6] to §2.2, the per-direction reading of Eq. (11) and the role of the current-state term to §3.1, the noise-level discussion to §3.2, and Tables R6–R7 to the appendix.
Response to Reviewer B58Y (1/3): summary; what is new and relation to prior solvers (W1)
We thank the reviewer for the expert reading and for [5, 6], which the revision cites and discusses in the related work. New results are on FFHQ (100 test images) for inpainting (r = 0.3) / SR 4× / motion deblurring.
Summary.
W1. What is new, and relation to DDRM, SNIPS, PC sampling and DiffPIR. The components of LARC are known. What is new is a correction step designed for the late stage of an existing solver.
1. The design. LARC takes over from a host at a late activation step and replaces only the remaining updates. Each corrected step has two parts, and one quadratic energy Ft (Eq. 10) defines both.
2. Other correctors in the same position. On each of the four hosts, after the same prefix and at LARC's total NFE, the remaining updates are replaced by FAST-DIPS, a SNIPS-style corrector (annealed Langevin with spectral preconditioning, on a geometric noise schedule down to 0.01) or LARC. Each competitor starts from its authors' recommended setting and is tuned per host and task over a range that contains it, on 10 development images (FFHQ 60000–60009, disjoint from the test set): for FAST-DIPS, ADMM penalty ∈ {175, 200, 225} and tolerance ∈ {0.04, 0.05, 0.06} (recommended: 200 and 0.05); for the SNIPS-style corrector, a step-size factor c ∈ {0.01, 0.018, 0.033, 0.06, 0.1, 0.2, 0.5, 1} and 1, 3, 5 or 10 updates per noise level, at most 5 on the DiffPIR host (official setting: c = 0.033, 5 updates). LARC keeps its Table 1 parameters. The code and all settings will be released.
Table R6. PSNR change (dB, computed before rounding) relative to the host continuing from the same state at the same NFE: FAST-DIPS / SNIPS-style / LARC. Brackets: that continuation (Table R1, reply to Reviewer 1jHd: A for DiffPIR; A′ for DPS and DAPS; the stronger of A and A′ for FAST-DIPS). "–": on the FAST-DIPS host, a FAST-DIPS late stage is the host's own continuation, i.e., the reference. Bold: best.
Only LARC improves every host on every task. Among the correctors it has the best SSIM in all 12 settings and the best PSNR in 11; on DAPS inpainting FAST-DIPS is 0.04 dB higher. The FAST-DIPS corrector falls below the host's own continuation in 3 of 9 settings, and the SNIPS-style corrector in 6 of 12.
3. Relation to the solvers named by the reviewer.
None of [1–4] puts the host's current state in the data step or applies K prior-score evaluations at one late level through that data step.