- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes Mean-Target Guidance (MTG), a training-free guidance rule for linear inverse problems. Rather than forming the measurement residual at the clean-image estimate or at the current state, it considers residuals at a continuum of "virtual targets" along the sampling path, weights them, and shows that the gradient reduces to a single residual at their weighted mean (the "mean-target"). With inverse-variance weights, each singular direction of the operator gets its own target and damping factor, both precomputed. MTG works with diffusion (EDM) and flow-matching models and outperforms strong training-free baselines on standard linear tasks.
Critical strengths
- The paper is well written and easy to follow. The method appears cheap (no backpropagation through the network, with per-direction quantities precomputed) and applies to both diffusion and flow-matching backbones, which would make it practically useful.
- MTG outperforms strong training-free baselines on most tasks and datasets, often by clear margins.
Critical weaknesses
W1. The proposed mechanism does not clearly drive the gains.
- The appendix notes that on the benchmark operators, the direction-specific target and damping are either constant across directions (masks share a single singular value) or saturated over most of the spectrum (blur/SR spectra lie mostly far below the noise level). The per-direction adaptivity is therefore mainly exercised on the synthetic operator, and the benchmark gains cannot be clearly attributed to it.
- In the ablation on the EDM backbone, the mean-target adds little over a fixed current-state target once the derived damping is used, whereas removing the damping causes a large drop. The damping itself resembles standard per-singular-value (Wiener-type) filter factors, as in DDRM and ΠGDM, and this connection is not discussed.
- The support ( vs. ) directly determines the target, but its choice is not motivated and varies across tasks and ablation rows.
W2. The "derived" target is largely a modeling choice.
- The main theorem follows from the residual being affine in , so the target is more so determined by the chosen weighting rather than by the theorem itself.
- The inverse-variance weighting relies on simplifying assumptions, and its form differs between the EDM and OT backbones. Alternative continuous weightings are not explored, and directly trained targets and step sizes (TTG) outperform the derived pair (MTG). Together, this suggests the derivation is more heuristic rather than a principled choice.
Questions for authors
- What set of images were used to tune the hyperparameters? Please also report runtime compared with the baselines.
- Results with both supports for all tasks, with some guidance on when to use each.
- A comparison with alternative weightings (e.g., uniform, or using the mode instead of the mean).
10 comments
Response to Reviewer kKXP (2/8)
W1 (first point) · Direction-specific adaptivity on the benchmarks (continued)
§4.2 separates the two derived components, the mean-target and the damping factor, by replacing each with fixed alternatives, with mixing and turned off (). It is not an ablation of per-direction processing. The two components can be separated only where both vary across directions, which requires singular values spread across the noise level with no direction falling far below it. Each benchmark setting misses one of these conditions: it has a single singular value, keeps its whole spectrum above the noise level, or places a large share of its directions far below it. We therefore constructed the spatial exposure operator for §4.2. We acknowledge that the manuscript did not convey this intent clearly, and that per-direction processing itself was not ablated in the submission. To avoid this confusion, we have also revised the main text. §3.2 now states that the mean-target differs between operators and, within one operator, across directions with different singular values. §4.1 refers to the direction-sharing ablation, and the opening of §4.2 states that the experiment measures what each component contributes rather than testing per-direction processing.
We have now run that ablation (Table R1) and added it to the revision in Appendix F.1.5, with the §4.2 rows in Appendix F.2.3. The target and the damping both come from the same per-direction variance , so turning per-direction processing off means sharing both. We replace each by its average in both rules, keep the actual and in the update, and retune . Sharing lowers all three metrics in all eight benchmark settings that have a spectrum (on average dB / / ), and the loss grows with how differently the directions are measured.
| Operator | Directions | PSNR change when shared |
|---|---|---|
| Box, Rand, Dn, OT SR | One singular value | 0 (identical by construction) |
| EDM SR | Spectrum entirely above the noise level | / (FFHQ / ImageNet) |
| EDM GB, EDM MB, OT GD | Spans the noise level, mostly below it | to |
| §4.2 graded operator | Spans the noise level | (EDM) / (OT) |
The benchmark blurs are realistic operators whose spectrum crosses the noise level, with singular values both above and below it, and sharing lowers all three metrics on each of them. Sharing matters even where the targets coincide: on EDM super-resolution only the damping differs across directions, yet sharing lowers all three metrics on both datasets.
Sharing fails because it summarizes the spectrum by its average energy. On EDM Gaussian blur, the shared target stays inside the per-direction range (noise level 3.16 against 2.84–3.70 at ), so sharing mainly changes the damping, and one value replaces the whole range: against – at , and against – at . The strongly measured directions then take much larger steps than their own damping sets, and one global cannot correct this without also shrinking the steps of the weakly measured directions. On OT Gaussian deblurring, sharing collapses both components: at , the shared target is against –, and the shared damping is against –.
W1 (second point) · EDM ablation and Wiener-type filters
We agree that the mean-target adds little over the current-state target once derived damping is used on EDM in §4.2. On that operator, EDM's directions differ mainly in the damping, which both rows share. With the damping removed (, ), the mean-target improves all three metrics on both backbones: 21.83 / 0.641 / 0.296 vs. 20.34 / 0.374 / 0.446 on EDM, and 22.14 / 0.699 / 0.196 vs. 18.78 / 0.458 / 0.400 on OT (submitted Table 2). The EDM mean-target rows with and without damping were selected with different supports, so their difference also includes a support change.
The similarity to spectral filters is real. The damping factor has the Wiener/Tikhonov form and shares its spectral principle with ΠGDM and DDRM, and the revision now discusses this connection in Appendices C.4 and D.3. The coefficient is a modeling choice made for a specific goal (Appendix C.4). We wanted the damping factor to depend on both the mean-target and the current sampling time, and adopting ΠGDM's weighting directly would not place the mean-target inside the factor. We therefore defined the step as the minimizer of a regularized displacement (Eq. 3.9) and set to the ratio of the measurement-noise variance at the mean-target to the conditional variance at the current step. The resulting form coincides with these filters.
Response to Reviewer kKXP (3/8)
W1 (third point) and Q2 · Choice of support
We ran all 20 settings under both supports (Table R2; Appendix F.1.5 of the revision), keeping the other hyperparameters fixed and selecting again for the alternate support. On EDM, switching SR, Gaussian blur, motion blur and random inpainting from look-forward to full support degrades all three metrics even after retuning, by 1.77–12.93 dB PSNR. For weakly observed directions, the weight is nearly flat, so the mean-target moves to the midpoint of the support. On EDM's full support, , this is a noise level of about 50 regardless of the current step, which late in sampling extrapolates far toward the noisy side, whereas the look-forward midpoint follows the current noise level. EDM box inpainting is insensitive in PSNR (within 0.14 dB), while SSIM clearly favors the submitted full support (0.872 vs. 0.781 on FFHQ, 0.773 vs. 0.716 on ImageNet). On OT, the alternate support stays within to dB after retuning, but perceptual metrics can still differ: on AFHQ-Cat box inpainting, it gains 0.17 dB while LPIPS worsens from 0.055 to 0.072. These results show that the support is not an incidental detail.
The integration interval must be fixed to define the objective, and the space of all intervals cannot be searched for an optimum. We therefore use one interpretable criterion, whether to include the noisier side of the current state: the look-forward support excludes it and the full support includes it. We treat this choice like other hyperparameters, selected per operator on validation, rather than as a fixed prescription, and other intervals, such as a window of fixed width around the current time, are equally possible. In practice, we recommend look-forward support on EDM (box inpainting can use either) and either support on OT. That we cannot identify an optimal support is a limitation, which the revision states in Appendix F.1.5.
Response to Reviewer kKXP (1/8)
We sincerely thank the reviewer for the thoughtful review, and for noting the clarity of the paper and the practicality of the method. Below we address each point. New results report PSNR ↑ / SSIM ↑ / LPIPS ↓ on 100 test images, and the tables are collected at the end of this response.
W1 (first point) · Direction-specific adaptivity on the benchmarks
Operator adaptivity does not come from the per-direction form. Our weight is the inverse of the residual covariance C(τ)=(1−τ)2AA⊤+τ2σy2I (Eq. 3.4), which already contains the operator. The weight, the mean-target and the damping therefore change with the operator even without the diagonalization from Eq. 3.4 to Eq. 3.5. Our new ablation confirms this: when the spectrum is summarized by a single average σ2=∥A∥F2/m, the target and the damping still change from operator to operator.
What the diagonalization adds is that each measured direction receives its own target and its own update strength, which is possible because the target is a variable. One rule can then cover operators whose directions are measured very differently. When the directions are measured alike, as with masks, the per-direction rule reduces to the shared one at no cost, and when they differ strongly, the per-direction rule is what keeps the sampler accurate (Table R1).
On the benchmarks, operator adaptivity shows first as a difference between operators. Each operator receives its own pair of curves over the sampling steps, one for the mean-target and one for the damping factor (Appendix F.1.3, Figs. 6–8, top and bottom rows), and masks, super-resolution and the blurs each receive a different pair. We kindly ask the reviewer to compare these curves across operators.
Within one benchmark operator, the mean-targets differ little, and this follows from the benchmark operators themselves. Only 8 of the 20 benchmark settings have more than one singular value.
The damping factor, by contrast, differs strongly across directions on every benchmark operator with a spectrum. This is where per-direction processing acts most visibly on the benchmarks, and we would particularly ask the reviewer to look at the bottom rows of Figs. 6–8.
The target and the damping come from the same per-direction variance Cs(τ). Where a benchmark operator leaves the targets close together, the same construction still gives each direction its own damping.
The spread of the targets also depends on the support. Look-forward support, the usual choice on EDM, confines every mean-target between σmin and the current noise level, so the spread in noise level is bounded by the current noise level and shrinks as sampling proceeds. With full support, targets can fall on both sides of the current state. This happens in OT Gaussian deblurring above and in the OT setting of §4.2, where the targets span τˉ=0.41 to 0.88 at t=0.51.