- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
AnisoLift enhances precomputed coarse particle-liquid trajectories while keeping the particle count fixed. It predicts per-particle position and velocity corrections and attaches an anisotropic covariance to represent local structure learned from paired high-resolution simulations. The corrections are applied to each saved frame and are not fed back into the solver. Results cover SPH and MPS simulations in both 2D and 3D, with position, velocity, kinetic-energy, and limited free-surface evaluations.
Critical strengths
-
The fixed-particle setting is useful. The method improves coarse states without adding particles or changing the solver, and the results cover several 2D and 3D SPH/MPS cases. This makes the representation idea relevant where a full high-resolution rollout is too costly.
-
The surface diagnostics add evidence beyond particle-wise errors. On 2D dam break, the reported occupancy IoU, F1, and surface-height error improve for both SPH and MPS. The anisotropic geometry also gives a plausible way to encode local directional structure at fixed particle count.
Critical weaknesses
-
Much of the quantitative evaluation remains close to the constructed high-resolution supervision targets. The paper does include independent-form surface diagnostics, but only for 2D dam break. It is hard to judge from the current experiments whether the corrections improve broader physical behavior, particularly temporal consistency and conservation across the sequence. This limits how far I can interpret the particle-wise gains.
-
The method corrects each precomputed frame independently and does not feed its output back to the solver. The paper acknowledges that it cannot repair a global transport mode missing from the coarse trajectory. This is a reasonable scope choice, but it narrows the claim of liquid enhancement. The current results do not quantify how stable the corrected states and anisotropic footprints are between adjacent frames.
Questions for authors
-
Could the authors report a sequence-level measure of temporal variation for corrected positions, velocities, and covariance orientations, alongside the coarse and high-resolution trajectories? A short visualization alone would not settle this concern.
-
Can the surface-level evaluation be extended beyond 2D dam break, or can the authors report frame-to-frame changes in momentum and kinetic energy relative to the high-resolution trajectories?
-
In the runtime table, does the stated inference time include feature extraction? The text says feature extraction dominates, while the table describes an MLP forward-pass timing. Please give end-to-end post-processing cost if available.
5 comments
Q2.1 Surface metrics. This requires a free surface. While in TGV and RPF the fluid fills a periodic box and in LDC it fills a closed cavity, so none of them has a free surface, the occupancy is full (IoU = 1 for every method) and the height profile is undefined. Those scenes are not proper to be evaluated at surface level. The change is in the fourth paragraph of section 4.4 in our manuscript highlighted in blue.
Q2.2. Frame-to-frame changes in momentum and kinetic energy relative to the high-resolution trajectories. We thank the reviewer for highlighting this important aspect of physical consistency. This comment led us to evaluate conservation properties according to the underlying physics of each simulation scenario. Following this suggestion, we have extended our evaluation to explicitly examine momentum and kinetic energy evolution across three scenarios, and show results in the Table R3-2 below. We highlight the corresponding manuscript change in blue in the section E of the appendix in the revision.
Specifically, kinetic energy is not expected to remain constant in any of the three scenarios, since it changes due to gravity and viscous dissipation in 2D DAM, whereas in both 2D and 3D TGV scenarios, it exhibits an overall decay due to viscous dissipation. We therefore compare its temporal evolution and frame-to-frame changes with those of the high-resolution reference. In contrast, total fluid momentum is theoretically conserved in the periodic and force-free TGV settings (up to numerical errors), and we evaluate the magnitude of its frame-to-frame change, which should vanish. In 2D DAM, where gravity and wall interactions exert external forces on the fluid, we instead compare its temporal evolution with that of the high-resolution reference.
Coarse and our corrected trajectories, we compute fluid specific kinetic energy and total momentum per frame, take increments , ; , and report Mean : (likewise Mean ), Rel. error of $ \Delta e_t = \frac{\sum_t \vert \Delta e_t - \Delta e_t^r \vert }{\sum_t \vert \Delta e_t^r \vert} $, $ \Delta \mathbf P_t = \frac{ \sum_t \Vert \Delta \mathbf P_t - \Delta \mathbf P_t^r \Vert_2 }{\sum_t \Vert \Delta \mathbf P_t^r \Vert_2} $ in the Table R3-2 below. Mean and Mean measure how large the per-frame change. The two Rel. error columns measure how far the per-frame changes are from those of the reference, in units of the reference’s own change, lower is better. Each trajectory is computed on its own particles, values are means over frames, then mean ± std over test trajectories.
Note that “—” appears only in the Reference rows of the Rel. error columns. A relative error of the reference to itself is zero by definition and carries no information, while “n/a” marks a quantity that is undefined in that scene. In the periodic TGV box the reference changes total momentum only at round-off level, so dividing by it gives a meaningless number. We therefore leave Rel. error of undefined there and assess conservation from Mean instead. As shown by the numerical results in the table below, compared to coarse particles, AnisoLift yields trajectories whose Mean and are closer to those of high-resolution reference particles, meanwhile, AnisoLift's trajectories enjoy lower relative error of and than coarse trajectories.
Table R3-2. Frame-to-frame changes in momentum and kinetic energy relative to the high-resolution trajectories.
| Scene | Method | Mean | Rel. error of ↓ | Mean | Rel. error of ↓ |
|---|---|---|---|---|---|
| 2D Dam break | Reference | — | — | ||
| 2D Dam break | Coarse | $0.940\pm 0.054 $ | |||
| 2D Dam break | Ours | $0.136\pm 0.039 $ | $0.899\pm 0.043 $ | ||
| 2D TGV | Reference | — | n/a | ||
| 2D TGV | Coarse | n/a | |||
| 2D TGV | Ours | n/a | |||
| 3D TGV | Reference | — | n/a | ||
| 3D TGV | Coarse | n/a | |||
| 3D TGV | Ours | $0.170\pm 0.099 $ | n/a |
W1. Quantitative evaluation remains close to the constructed high-resolution supervision targets. Like learned Lagrangian simulators such as GNS or Neural SPH, we supervise with high-resolution simulation data. Unlike them, coarse and high-resolution particles do not correspond one-to-one, so each coarse particle’s target is a projection of the reference onto it, i.e., a kernel average of its high-resolution neighbors, in the spirit of Yu & Turk (2013). Table 1 measures how well this projection is recovered.
Q3. Does the inference time include feature extraction? No, Table 8 timed only the MLP forward pass. We now time the full processing of one frame, from the coarse states to corrected positions, velocities and covariances in the Table R3-3 below. Post-processing time spent is less than one single solver step in that frame on both scenes. We highlight this manuscript change in blue in the section B.2 of the revision.
Table R3-3. Full processing time of one frame.
| 2D DAM | 3D TGV | |
|---|---|---|
| Number of Coarse/High-resolution particles | 1,622/5,740 | 1,000/8,000 |
| Complete feature extraction | 420 s | 400 s |
| MLP forward pass incl. assembly of | 5.8 s | 6.3 s |
| Apply corrections, copy results back | 160$\mu$s | 160$\mu$s |
| AnisoLift total | 585.8 s | 566.3 s |
| Coarse solver | 1,680 ms | 593 ms |
| High-resolution solver | 2,023 ms | 2,482 ms |
| Post-processing over the coarse solver | 0.035% | 0.095% |
| Post-processing over the high-resolution solver | 0.029% | 0.023% |
Q1 and W2.1. Stability of corrected states and ellipsoids between adjacent frames.
We sincerely thank the reviewer for highlighting the important issue of temporal stability in AnisoLift, which prompted us to conduct additional experiments. We provided a sequence-level measure of temporal variation for the corrected positions, velocities, and covariance orientations, alongside both coarse and high-resolution reference trajectories, as shown in the Table R3-1 below. These results were obtained on SPH simulation data for 2D DAM, 2D TGV, and 3D TGV. Apart from the MSEx and MSEv metrics already employed in our paper, four further metrics were introduced to quantify the temporal variation of position, velocity, ellipsoid rotation, and covariance orientations. These indicators are calculated as follows, Between consecutive frames, each column’s own particles give the second differences δ2x=∥xt+1−2xt+xt−1∥2 (the same to δ2v), the log-Euclidean change dLE(C)=∥logCt+1−logCt∥F, and the rotation ΔθC=arccos∣ut+1⊤ut∣, with u the unit major eigenvector of C. Since the "Reference" represents the ground truth, its MSEx and MSEv values are denoted by "-". Furthermore, as neither the "Coarse" nor the "Reference" results contain ellipsoidal particles, orientation-related metrics are not applicable, these entries are marked as "n/a." These results indicate that, compared to the "Coarse", AnisoLift’s temporal variations are closer to those of the "Reference." We highlight the manuscript change in blue in the new section D of the revised appendix.
W2.2. Support to our claim of liquid enhancement.
We particularly appreciate the reviewer’s recognition that our frame-wise refinement is a reasonable scope choice. At the same time, we acknowledge the valid concern raised in W2 regarding the scope of our claims about liquid enhancement. We thus implemented a centered smoothing approach applying a 3 or 9-frame moving average to the outputs of AnisoLift to support our claim (Ours+MA3, Ours+MA9 in the Table R3-1 below). Our results indicate that this simple method brings the magnitude of position and velocity temporal variation closer to the reference. In future work, we intend to develop a more robust mechanism to ensure positive outcomes across a broader range of scenarios as mentioned in Section 5.
Table R3-1. Sequence-level measure of temporal variation for corrected states.