- Rating
- 2
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper uses a PnP framework for image regularization, similar to PnP Flow Matching. In contrast to PnP Flow the authors use an ADMM framework instead of the forward backward splitting. Further they provide similar analysis for an averaged operator, which averages the denoising step for several Monte Carlo Samples z. The algorithm outperforms PnP Flow and Flower on standard image restoration tasks on CelebA and Cats.
Critical strengths
-
The performance is genuinely strong. There are for instance strong gains in superresolution or random inpainting on CelebA.
-
The paper is nicely written and justifies their algorithm somewhat theoretically.
Critical weaknesses
-
First of all the averaged operator is alreadz done in PnP Flow at least empirically. They average over 5 samples, so defining the operator itself is not novel. Further, the convergence statements obtained are weak in practice.
-
Proposition 1 is weak since it essentially requires the operator to be 1 Lipschitz. This is, for a trained velocity field, on highly multimodal data essentially unavailable.
-
The convergence statement is standard in Proposition 2, similar to PnP Flow and does not address to what point it converges to. This would be genuinely interesting, because with Liopschitz velocity and the (1-t) multiplication it is to no surprise that the algo converges.
-
I am wondering where the gain in the numerical section really stems from. Since they optimize a bit different, I would love to see an ablation on PnP Flow and ADMM with the same grid. Because otherwise i do not concur with the thesis that ADMM is the factor that separates the methods, it might as well by hyperparameter optimization. I am aware that the late schedule has been applied to PnP Flow, but i would like to see a proper comparison with the same amount of hyperparams, same tuning budget to be fully convinced.
-
There is already work unifying PnP methods and ADMM with flow based denoisers, see [1]. They in particular have in depth theoretical analysis although they do not share the renoise denoise framework, so a comparison with those algorithms (and the same pretrained velocities) would strengthen the submission.
Overall, I find the novelty to be very limited with respect to prior work and the outperformance of empirical results cannot be clearly enough attributed to the use of ADMM (which is not new).
[1] Taming Score-Based Denoisers in ADMM: A Convergent Plug-and-Play Framework, Shrestha et al, ICLR 2026
Questions for authors
see weaknesses