- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
This paper introduces a two-step explicit mesh generation method. The first step (v-flow) generates vertices and the second step (t-flow) generates the connects in-between vertices.
The main benefits are high-quality, controllability.
The main concrens are a) unclear explanation why factorization is resonsible to the benefits. b) limited novelty of the core factorization idea.
Critical strengths
The overall improvements across all four metrics in Table 1.
Critical weaknesses
-
Insufficent evidence for the benefits of factorization. Although the factorization is natural and the authors claim that seperating vertex and topology simplifies flow learning and reduce broken surfaces. However, the paper lacks controlled comparison between joint and factorized flow models. Since the proposed methods also introduce several architectual changes, it's unclear whether the observed improvments are directly from factorization.
-
Unclear effectiveness of vertex-conditioned topology generation. The authors claim that realized vertices simplifies connectivity prediction. However, similar vertex can correspond to different valid topologies. For example, a empty bottle (has inner surface and outer surface) and a solid bottle (only outer surface), similar vertex structures but different topologies. It remains unclear how the proposed method handles such cases.
-
Limited conceptual novelty of the core factoization idea. The decomposition of mesh generation into vertex-topology prediction has been explored in prior works. Such as PolyGen, Nexus.
Questions for authors
-
Can the authors provide a more controlled comparison between joint and factorized flow models to demonstrate that the factorization itself simplifies learning and improves mesh quality?
-
How does proposed method handle empty/solid bottles? this case study would help calrify when factorization is beneficial and where it may struggule.
-
Could the authors clarify the novelty of the proposed factorization compared with prior works such as PolyGen and Nexus? In particular, what are the key methodological advances beyond applying flowing matching to existing two-stage framework?
-
In qualitative results of Figure 5, if we repair broken surface regions from baseline methods via boundary triangulation or surface interpolation, how is the results compared with LATO.2?
2 comments
Rebuttal by Authors [2/2]
W3 & Q3: Methodological Novelty Relative to PolyGen, FastMesh, and Nexus
While predicting connectivity after vertices has precedents in PolyGen and FastMesh (which we have credited explicitly in Line 257-263 in the revision pdf), LATO.2 differs fundamentally in its latent representation and continuous generative formulation:
- Comparison with PolyGen and FastMesh: PolyGen relies on autoregressive decoding for both vertices and faces, incurring prohibitively slow inference. FastMesh pairs autoregressive vertices with direct feed-forward adjacency prediction; while fast, this deterministic predictor produces severe face redundancy (evidenced by its face-to-vertex ratio and 65.00% non-manifold edges in Table R2).
- LATO.2 Formulation: Rather than using autoregressive or deterministic feed-forward predictors, LATO.2 learns separate continuous latent spaces for vertices and topology. Connectivity is encoded via adjacency-masked attention and sampled through conditional flow matching over realized vertices and voxels—providing a learned, probabilistic topology distribution suited for generative sampling.
- Comparison with Nexus: As noted around Line 105 of the main paper, the closest concurrent work, Nexus, uses a coarse-to-fine octree diffusion model that generates vertices level by level, making it considerably slower than LATO.2's single-pass structured latent decoding. For topology, Nexus uses graph autoencoding supervised by a SpaceTime loss, whereas LATO.2 trains its topology latent with a contrastive objective and extracts faces via loop detection. Moreover, Nexus has not publicly released its code; our open-source release will provide a reproducible benchmark for factorized mesh generation.
As shown in Table R2 (evaluated on identical input vertices), T-Flow outperforms both PolyGen and FastMesh in geometric accuracy ( and ), normal consistency (), Topology Score (), and manifoldness (), while running over faster than PolyGen.
Table R2: Comparison with factorized vertex-and-topology generation methods on identical input vertices.
| Method | Time (s) | Face Count | F/V | NM (%) | |||||
|---|---|---|---|---|---|---|---|---|---|
| GT | - | - | - | - | 0.723 | - | 2538 | 1.92 | 1.07 |
| PolyGen | 16.68 | 2.725 | 1.848 | 0.799 | 0.612 | 174.5 | 2371 | 1.79 | 14.32 |
| FastMesh | 1.274 | 0.078 | 0.373 | 0.923 | 0.619 | 0.245 | 7435 | 5.62 | 65.00 |
| T-Flow (Ours) | 1.247 | 0.051 | 0.368 | 0.964 | 0.634 | 1.338 | 2653 | 2.01 | 6.68 |
Q4: Post-Hoc Boundary Triangulation / Hole Filling on Figure 5
Following your suggestion, we applied post-hoc boundary triangulation to the generated meshes of every method. Specifically, we detected closed loops formed by open boundary edges and triangulated each loop containing fewer than edges.
Table R3 reports the resulting metrics and deltas after hole filling. Overall, post-hoc triangulation yields negligible or slightly negative changes across baselines (particularly in and ) and fails to narrow the performance gap with LATO.2. This occurs for two reasons:
- Most broken regions observed in Figure 5 are not bounded by clean, closed loops of open boundary edges (often involving non-manifold or disconnected adjacent edges), so boundary triangulation repairs only a small fraction of defects.
- Blindly triangulating boundary loops frequently seals legitimate openings in valid structures, degrading normal consistency and topological regularity.
These results confirm that LATO.2’s advantages arise from intrinsically cleaner connectivity generation rather than surface artifacts that could be trivially patched in post-processing.
Table R3: Performance and metric deltas ( relative to raw outputs) after boundary-loop hole filling on generated meshes.
| Method | Type | ||||
|---|---|---|---|---|---|
| BPT | AR | 0.0604 (+0.0001) | 0.1075 (+0.0008) | 0.8095 (-0.0016) | 0.7764 (-0.0003) |
| DeepMesh | AR | 0.0530 (+0.0001) | 0.0964 (+0.0018) | 0.8192 (-0.0026) | 0.8036 (-0.0017) |
| MeshRipple | AR | 0.0458 (-) | 0.0951 (+0.0010) | 0.8173 (-0.0001) | 0.7794 (-0.0002) |
| MeshFlow | Flow | 0.0459 (+0.0004) | 0.0780 (+0.0008) | 0.8225 (-0.0002) | 0.6881 (+0.0001) |
| LATO | Flow | 0.0424 (+0.0003) | 0.0726 (-0.0012) | 0.8220 (-0.0042) | 0.8050 (-0.0007) |
| LATO.2 | Flow | 0.0407 (-) | 0.0660 (+0.0003) | 0.8340 (-0.0001) | 0.8095 (-) |
Rebuttal by Authors [1/2]
We sincerely thank the reviewer for the insightful feedback and constructive suggestions. We respectfuly explain that our core contribution lies in factorizing and coupling dedicated vertex and topology latent spaces for native mesh flow matching. This generative formulation directly enables scalable mesh synthesis, part-wise refinement, and topology-adaptive editing. Prior decoupled methods rely on either slow autoregressive decoding or deterministic prediction prone to topological redundancy, whereas our probabilistic latent flow design achieves both fast inference and clean connectivity. Thus, high-level conceptual precedents do not diminish the novelty or empirical significance of our framework.
Below, we isolate the architectural gains of our factorized latent framework, clarify how coarse voxel conditioning resolves topological ambiguity for identical vertex sets, distinguish LATO.2 from prior vertex-first approaches, and evaluate post-hoc boundary-based hole filling on the generated meshes.
W1 & Q1: Isolating the Contribution of Factorization
We agree that isolating factorization from resolution, offset prediction, and training data is critical.
LATO.2 @64-512 (no offset)still outperformsLATO @128-512across every metric—most notably reducing Hausdorff Distance from 0.0738 to 0.0679. This confirms that factorization itself reduces topological holes and improves structural fidelity.Table R1: Controlled ablation isolating latent factorization from decoding resolution, offset prediction, and model size.
W2 & Q2: Effectiveness of the vertex-conditioned topology generation
To clarify both the empirical efficacy of T-Flow and how it disambiguates identical vertex sets (such as empty versus solid bottles), we highlight two key aspects of our design:
Consistency & Robustness: Table 4 of the original paper evaluates T-Flow conditioned on both ground-truth vertices and V-Flow generated vertices, demonstrating strong robustness to vertex perturbations. Furthermore, when compared directly against a deterministic connectivity predictor (FastMesh) on identical ground-truth vertices (Table R2 and Figure 6 in the revision pdf), T-Flow yields substantially cleaner and more consistent topology.
Resolving Identical Vertices with Different Topologies (Empty vs. Solid Bottle): Crucially, T-Flow is not conditioned solely on raw vertex coordinates. As illustrated in Figure 2 of the main paper, it is also conditioned on the coarse 643 voxel occupancy grid, the same initial scaffold provided to V-Flow, which supplies volumetric cues about interior partitions and surface boundaries.
Case Study (Figure 14, Appendix in the revision pdf, Page 21): We provide the exact bottle test case requested. Given the same set of bottle vertices, one 643 voxel condition specifies an internal horizontal partition while the other does not; T-Flow accurately reconstructs the appropriate distinct topology for each condition.
Sub-Voxel Ambiguity: When two valid topologies differ only at a fine sub-voxel scale where the 643 conditioning is identical, T-Flow draws a coherent sample from its learned conditional topology distribution.