- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
Variance Path Diffusion (VPD) models cumulative diffusion variance using Gamma distributions and introduces a time-varying-rate construction based on Beta thinning. Regional variance allocation provides a single control parameter spanning generation, editing, inpainting, and motion in-betweening. Validation includes three image datasets, HumanML3D, and ablations of variance randomness and training mixtures.
Critical strengths
-
The Beta-thinning formulation preserves Gamma marginals and supports monotone variance paths with tractable conditional bridges. This provides a useful mathematical framework for designing regional noise schedules.
-
VPD improves most reported inpainting settings; for example, ImageNet wide-mask FID decreases from 56.7 to 38.5 relative to RAD. Motion experiments also show strong quality and keyframe accuracy, with baselines evaluated under matched keyframe spans. These results support practical value beyond the theoretical formulation.
Critical weaknesses
-
The shared-rate impossibility claim exceeds the demonstrated result. Corollary 3.2 bounds terminal variance variability when (A_1>1); it does not establish impossibility at every finite stochasticity parameter or concentration of the entire path. Moreover, (A_1>1) is a sufficient condition rather than a demonstrated requirement for successful training. This weakens a central motivation for the proposed construction.
-
VPD shows promising results on Table 2. However, the models requires a high NFE number and it is not clear if VPD works in one or few step generation (MeanFlow).
Questions for authors
-
What are the exact inside/outside variance schedules used for the reported results? Does Table 7 describe actual diffusion variance or a floor applied only to conditioning inputs? Please reconcile it with Appendix F.4.
-
Can the shared-rate claim be narrowed to the terminal-concentration tradeoff actually proved? What establishes that (A_1>1) is necessary for the practical training behavior being discussed?
-
Please provide the explanation if VPD can be extended to one or few step generation ?
2 comments
Dear Reviewer gC3X,
Thank you again for your careful review. We have posted our response and a revised manuscript. In particular, we narrowed the shared-rate claim to the trade-off that is proved, and added the few-step results.
As the discussion period closes soon, we would be grateful to hear whether the response addresses your concerns. We are happy to answer any further questions.
Best regards, Authors of Submission 48703
We thank Reviewer gC3X for their comments. The questions on the scope of the shared-rate claim and on the sampling schedules of Table 9 (prev. Table 7) and Appendix F.4 pointed to places where the paper was imprecise, and the question on few-step sampling led to a new set of experiments. We respond to each point below.
Q1: What is the exact inside/outside variance schedules? Clarify Table 7 and Appendix F.4
Table 9 (prev. Table 7) lists the inference settings used for all reported results. The floor σmin is applied to the total per-pixel variance of the path itself, and the denoiser receives the same floored map. There is no separate floor on the conditioning input. Reconciling with App. F.4, each region's level is γrσˉt with one fixed γ, clipped to [σmin,σmax].
Q2: Can shared-rate claim be narrowed to the terminal-concentration tradeoff? Is A1>1 necessary conditions?
We agree on both points. What we prove is a trade-off. Under a shared rate, A1>1 forces the relative deviation of the terminal variance below σmin/σmax (Prop. 3.1, Cor. 3.2). This does not show impossibility at every finite κ. Therefore, A1>1 is also sufficient and not necessary. Intuitively, it ensures that every Gamma marginal has a density that vanishes at zero, so probability mass does not pile up at the floor. FID stays flat down after the condition (Fig. 2(c)), and what tracks the degradation is the fraction of levels clipped at σmin (Sec. 3.2). We have narrowed the claim in the abstract, contribution (2), and Section 3 (marked in green).
Q3: Can VPD be extended to one or few step generation?
VPD is a multi-step sampler and we have not tested one-step generation. One-step and few-step methods either distill a multi-step teacher (Progressive Distillation [1]) or train a few-step map directly (Consistency Models [2] or MeanFlow [3]). Our construction instead changes the noise-level law used in training and the per-region levels used in sampling. Therefore we think these methods can be applied with VPD formulation, with the per-pixel level map as an additional input. We leave this to future work.
Table. R4 Few-step sweep on FFHQ box masks (FID / LPIPS). DDNM and DPS use the same model as VPD TVR with a different sampler. AsyncPatch is our reimplementation, trained with its level distribution on the same model.
However, we provide the few-step sweep results in Table. R4. DDNM and DPS use the same denoiser as VPD TVR but differ only in the sampler. VPD's few-step behavior comes from conditioning through the level map together with training that covers it. The preserved region enters the network at σmin from the first step, while DDNM and DPS see pure noise and impose the observation afterwards. AsyncPatch is our model trained with AsyncPatch's level distribution (as in Table 3), so it uses the same per-pixel level map and sampler. "w/ Thm C.2" uses the closed-form reverse covariance with the learned diagonal Σ0 head and "w/o" uses the standard ancestral variance. AsyncPatch uses the same map and sampler but rarely trains on a region held at the floor, which breaks at NFE 4.