- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies few-step generation of complex-valued fields. It models amplitude and phase using cylindrical geometry and combines this with optimal-transport coupling. The authors analyze angular-velocity behavior near zero amplitude under straight-line interpolation and compare paths and couplings on synthetic data, complex MRI fields, and audio representations. The task is distribution generation, rather than MRI reconstruction from measurement constraints.
Critical strengths
- The paper identifies a concrete, testable geometric problem. Under equal amplitudes and uniformly distributed phase differences, Cartesian straight-line paths produce heavy-tailed angular velocities, whereas shortest-arc paths avoid this particular conditional-path problem. Crossed ablations of geometry and coupling also help separate their effects. This provides an interpretable insight whose value goes beyond a score improvement.
- The failure cases expose an important limitation of the evaluation metrics. On high-resolution MRI, better pooled pixel-distribution scores at one sampling step do not translate into better spatial structure. The patch-reassembly experiment also illustrates dependencies that pooled distribution measures can miss. These results do not establish overall success, but they provide useful diagnostics and show that the authors report unfavorable findings.
Critical weaknesses
- The conditional-path properties are not yet sufficiently connected to the few-step advantage of the learned generator. Flow matching on manifolds and optimal-transport coupling have direct precedents. The added contribution must therefore come from what this specific geometry achieves for complex fields. Bounded angular velocity along a shortest-arc path does not imply bounded network predictions or smaller few-step integration error. The Cartesian network regresses endpoint differences, rather than the angular velocity induced by the straight path. The paper reports that network predictions can exceed the path bound and includes a tanh-constrained experiment, which are useful controls. However, changing geometry also changes the path, parameterization, and metric used to measure velocity error. The experiments do not yet directly connect these changes to errors in the learned field. The more-stable-regression claim on page 6 and parts of the mechanistic attribution on page 17 should therefore be limited to what is established.
- The main distribution metrics do not establish better generation of complete complex-valued fields. Sliced W2 over pooled pixels is insensitive to spatial rearrangement and cannot by itself characterize dependencies between locations. In the 320×320 MRI experiments, CyFM is worse than the reported Cartesian controls on all spatial metrics at every evaluated step count. This directly limits the main quality claim. The evidence supports better few-step fitting of certain marginal distributions, but not an overall improvement in complete MRI structure or audio-waveform quality. 3.In the k=4 column of Table 6 on page 17, lower Sliced W2 is better. CyFM+OT has 0.1121, while Cartesian+OT has 0.1166, but the latter is boldfaced. Please correct the best-value marker. This is a table-formatting error. It does not change the reported numbers or independently determine my recommendation.
Questions for authors
1.Which controlled results directly support easier few-step integration of the learned field, beyond improved conditional target angular velocities? 2.Given the deterioration in spatial metrics on 320×320 MRI, what is the main generation-quality claim that the authors consider established? 3.Do the few-step and speedup claims refer to integration steps, network evaluations, or measured runtime? How do differences in evaluation cost affect the comparison?
2 comments
Thank you for authors' response and clarifications which address several of my concerns. I would keep its original rate.
We thank the reviewer for the precise, constructive review and for recognizing both the testable geometric problem and the insights from our crossed ablations and failure analyses. All revisions below are incorporated in the updated manuscript.
W1: Our novelty is what the cylindrical geometry gives complex-valued fields, while the manifold and OT machinery are prior work that we cite (Chen & Lipman, 2024, and Bose et al., 2024). We contribute (i) a proof that the cylindrical angular target is bounded by π for any coupling, against an index-1 Pareto tail for Cartesian bridges, with 42.6–49.4% of signal energy above π on real data (Table 1), (ii) the finding that whole-field OT must stay joint, because factorising it over amplitude, phase, or patches changes the target distribution (Section 5.4), and (iii) an exact one-step result (Proposition, Appendix B): one solver step keeps the mean data amplitude on the cylinder but shrinks it in the plane, which gives a 1.7–2.4× lower one-step amplitude error in all four blocks. At 320×320, where OT is inert, the one-step advantage holds even without coupling (pooled 0.058 vs. 0.135), so it comes from the geometry. All of this runs on a standard real-valued U-Net, because the geometry lives in the transport.
W1, Q1: We narrowed three claims in the revised manuscript where conditional-path bounds went beyond what was established for the learned field:
To answer Q1 directly, Appendix B proves an exact link to the learned field: for any input parameterisation, one Euler step returns the conditional mean of the endpoint, which attenuates amplitude in the plane under phase uncertainty but preserves it on the cylinder. Measured in data space, one-step amplitude error is lower for CyFM across all four blocks with seeds separated.
W2: Pooled sliced W2 cannot characterize spatial dependencies by itself, as the patch-reassembly experiment shows (the metric reads 0.000 while cross-seam correlation drops from 0.979 to 0.044, Section 5.4). That is why our knee tables pair it with amplitude lag-one, circular phase lag-one, and radial-spectrum gaps, and why our revised claim keeps marginal and spatial results separate.
W2, Q2: The established claim is better few-step fitting of pixel-marginal distributions at matched network evaluations, carried by amplitude: at every k≤8 on synthetic fields and speech, and at k=1 on knee MRI at both resolutions (Appendix K). On knee 64×64, CyFM also leads from k=4 in 7 of 9 comparisons across Table 2's three spatial measures. As stated in the conclusion, we claim no overall improvement in complete 320×320 structure or in audio quality. At 320×320, an endpoint phase target (new Appendix J, see our reply to Reviewer 8t4Q on 320×320) shrinks the spatial gaps several-fold, leaving CyFM no worse than any Cartesian arm on any spatial measure at k=8.
W3: Thank you for catching this. We have corrected the bold marker in Table 7 (submitted Table 6).
Q3: Both "few-step" and the "25× fewer solver steps" in Section 5.2 refer to solver steps k. Because every flow arm uses the same Heun solver, k steps cost 2k−1 network evaluations of the same U-Net in every arm, and one evaluation takes the same time in both geometries: averaged over k, 0.515 vs. 0.513 ms on knee 64×64, with a cylinder/plane ratio of 1.00 also at 320×320 and with the larger backbone (one RTX 4070 Ti SUPER, measured for this reply). Step-count reductions therefore carry over directly to wall-clock time. All three units on knee 64×64:
We hope these revisions and clarifications address the reviewer's questions.