- Rating
- 2
- Confidence
- 1(−1)
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper composes Gaussian representations trained at different primitive budgets to obtain compact meshes. Starting from a low-budget representation, it replaces Gaussians where higher-budget candidates improve agreement with depth rendered from a high-budget reference. The composite is optimized and meshed using the underlying reconstruction method. Evaluation includes Gaussian Wrapping, MILo, and GGGS.
Critical strengths
- A relevant distinction between rendering and meshing. Allocating Gaussians for photometric reconstruction need not yield an efficient spatial structure for mesh extraction. Local budget allocation is a reasonable response.
- Evaluation includes geometric metrics. The paper reports Chamfer distance and F1 in addition to mesh-rendering quality, and tests multiple reconstruction backbones.
- Important limitations are disclosed. The appendix includes QEM comparisons, a matched-optimization single-budget control, full dataset results including Box, and discussion of reference-depth errors and input preparation cost.
Critical weaknesses
- The incremental value of multi-budget composition is small in the strongest control. At the default gamma = 0.2, Table 6 retains 95.57–99.83% of the original G4 Gaussians across backbones. For MILo, Table 12 compares both representations after the same 2K optimization: G4 gives 18.11 MB and CD 0.1342, versus 17.78 MB and 0.1341 for the composite. This is approximately 1.8% additional size reduction with nearly unchanged accuracy. Much of the headline reduction relative to G5 may therefore be obtained by selecting G4 and optimizing it. Equivalent controls across the other backbones are needed.
- The advantage over direct mesh simplification is conditional. The paper does compare against QEM at matched face counts; this baseline is not absent. Appendix H reports better CD for QEM throughout the tested MILo range, with additional reversals at smaller mesh sizes for other settings. The proposed method may avoid extracting the largest mesh, but peak extraction memory and end-to-end timing are not provided to establish that advantage.
- Depth-reference agreement does not guarantee geometric improvement. Selection is supervised by the highest-budget model, which need not have the most accurate geometry. On Box with MILo, Table 7 reports CD 1.93717 for G3, 4.42256 for the G5 reference, and 4.34694 for the default composite. The failure is acknowledged, but it limits the interpretation of the selection score as geometric gain. The criterion also does not directly account for the mesh-complexity cost of a replacement.
- Scope and computational cost need clearer contextualization. The main DeMapGS geometric aggregate excludes Box, although full results are provided in the appendix. On Tanks and Temples, Gaussian Wrapping’s default composite reduces size but also lowers mean F1 from 0.498 to 0.455 relative to G5. Moreover, the approximately 41–91 second composition-stage timings exclude multi-budget input preparation and extraction. These are conditional quality–cost trade-offs, not evidence of uniformly preserved geometry at negligible extra cost.
Questions for authors
Q1. Could the authors clarify how much improvement comes from multi-budget composition compared with directly optimizing a lower-budget representation? Extending the matched-optimization comparison in Table 12 to other backbones would help.
Q2. Could the authors report the total processing time and peak memory, including preparation of the multi-budget representations? This would clarify the practical trade-off relative to mesh extraction followed by simplification.
Q3. How sensitive is the method to the quality of the highest-budget reference depth? It would be helpful to discuss when this reference is reliable and how its errors affect the final mesh.
Q4. Could the authors evaluate the method on a wider range of challenging scenes where the baseline reconstruction quality is lower? Since the baseline PSNR is already high in several reported settings, it would be helpful to understand whether the method can provide more substantial quality improvements in these cases, alongside the gains in mesh compactness.
12 comments
W2 & Q2. Mesh Simplification, Extraction Memory, and Computational Cost
We acknowledge that QEM achieves better geometric accuracy in several settings, including the evaluated MILo configurations, as reported in Appendix H. However, the two approaches operate at different stages: QEM simplifies an already extracted mesh, whereas our method reduces Gaussian representation complexity before mesh extraction. This distinction can be particularly important when extracting a large intermediate mesh is limited by GPU memory.
1. Extraction Memory on Mip-NeRF 360
As reported in Sec. 4.5, extracting meshes from the original full-budget G5 representations of Gaussian Wrapping and GGGS on Mip-NeRF 360 results in out-of-memory (OOM) errors. Consequently, we constructed subsampled G5 representations for these two backbones, which were used for baseline mesh extraction and reference-depth supervision in Table 4.
To quantify the extraction-memory benefit, we additionally measured peak GPU memory during mesh extraction across all nine scenes of Mip-NeRF 360. The table reports the average peak GPU memory across scenes, with the maximum value in parentheses. Memory is measured in GiB. For Gaussian Wrapping and GGGS, G5 denotes the subsampled representation used in Table 4.
| Method | G5 (GiB) ↓ | G4 (GiB) ↓ | Ours () (GiB) ↓ | Reduction vs. G5 |
|---|---|---|---|---|
| Gaussian Wrapping | 2.708 (3.900) | 2.017 (2.928) | 2.026 (2.841) | 25.2% |
| MILo | 8.498 (9.918) | 7.753 (9.385) | 7.372 (9.209) | 13.2% |
| GGGS | 2.927 (4.506) | 2.474 (3.672) | 2.324 (3.496) | 20.6% |
Compared with the evaluated G5 representations, our method reduces average peak extraction GPU memory by 25.2% for Gaussian Wrapping, 13.2% for MILo, and 20.6% for GGGS. We also observe a consistent trend on DeMapGS, where peak extraction GPU memory decreases as increases across all three backbones (see our response to Reviewer ERz1, W1). This further supports the extraction-memory benefits of reducing representation complexity before meshing.
Compared with G4, extraction memory is further reduced for MILo and GGGS, while remaining nearly unchanged for Gaussian Wrapping. Nevertheless, as shown in Table 4, our method produces smaller meshes than G4 across all three backbones while improving mesh-rendering PSNR:
- Gaussian Wrapping: 156.48 → 144.38 MB (PSNR: 23.413 → 23.455 dB).
- MILo: 208.37 → 180.99 MB (PSNR: 22.867 → 23.510 dB).
- GGGS: 293.94 → 278.77 MB (PSNR: 22.903 → 23.106 dB).
These results demonstrate that our approach reduces extraction-stage memory requirements while maintaining competitive mesh-rendering quality. The OOM cases also highlight a practical advantage of reducing representation complexity before extraction: when the original full-budget G5 mesh cannot be extracted due to memory constraints, post-extraction simplification cannot be applied to that mesh.
2. Total Computational Cost
We also measured the total processing time and peak memory consumption, including multi-budget preparation and mesh extraction, to characterize the additional computational overhead of our approach.
The following results are averaged over five DeMapGS scenes (Book, Buddha, Bust, Cat, and Tree). Total processing time includes G5 preparation, additional G1–G4 preparation (for Ours), composition, final refinement, and mesh extraction.
| Measurement | GGGS (G5 / Ours) | Gaussian Wrapping (G5 / Ours) |
|---|---|---|
| Total processing time (min) ↓ | 29.10 / 44.38 | 16.77 / 35.58 |
| Overall peak GPU VRAM (GiB) ↓ | 15.941 / 15.941 | 2.561 / 3.380 |
| Overall peak CPU RSS (GiB) ↓ | 6.691 / 5.314 | 4.033 / 4.120 |
| Mesh extraction time (s) ↓ | 255.01 / 59.70 | 19.04 / 18.57 |
Our method incurs an additional 15.27 minutes for GGGS and 18.81 minutes for Gaussian Wrapping. For GGGS, the overall peak GPU memory remains unchanged at 15.941 GiB because the highest memory consumption occurs during G5 training, which is shared by both pipelines. In contrast, for Gaussian Wrapping, the overall peak increases from 2.561 to 3.380 GiB because the final Gaussian refinement stage requires more memory than the original G5 training stage. Nevertheless, mesh extraction becomes substantially faster for GGGS, with a 76.6% reduction in extraction time.
Overall, these results clarify the practical trade-off of our approach: additional offline preparation costs in exchange for improved geometry–mesh-size trade-offs and reduced extraction-stage resource requirements in the evaluated settings. While our method does not aim to minimize end-to-end reconstruction time, reducing representation complexity before mesh extraction can provide practical benefits, particularly when extracting the original full-budget mesh is memory-intensive or infeasible.
W3 & Q3. Reliability of Reference Depth and Its Impact on Mesh Reconstruction
We agree that the highest-budget representation does not necessarily provide the most accurate geometry, and that agreement with its depth does not guarantee improved ground-truth geometry. As described in Sec. 3.2, G5 depth serves as a geometric proxy rather than ground-truth geometry. Severely inaccurate reference geometry, as observed in the MILo Box scene, can therefore limit the effectiveness of our method. This limitation is already discussed in Appendix J.
1. Sensitivity to Reference-Depth Errors
To evaluate how reference-depth errors affect the complete pipeline, we applied spatially coherent 3D perturbations to G5 and used the resulting reference for both Gaussian selection and the subsequent 2K refinement. This extends our selection-only sensitivity analysis (see our response to Reviewer ERz1, Q1), in which the original G5 reference was retained during refinement.
Experimental setup. We evaluated MILo on five DeMapGS scenes (Book, Buddha, Bust, Cat, and Tree), using and . Perturbation magnitudes were calibrated relative to the original G5-to-GT depth RMSE, following the same protocol as our selection-only experiment. Geometric deformations become visually noticeable at 0.25 × RMSE and substantial at 1.0 × RMSE.
| Reference perturbation | CD ↓ () | Mesh (MB) ↓ | CD ↓ () | Mesh (MB) ↓ |
|---|---|---|---|---|
| Original G5 | 0.1341 | 17.78 | 0.1579 | 9.16 |
| 0.1 × RMSE | 0.1348 | 17.73 | 0.1585 | 8.76 |
| 0.25 × RMSE | 0.1357 | 17.43 | 0.1637 | 7.70 |
| 0.5 × RMSE | 0.1407 | 16.63 | 0.1775 | 6.22 |
| 1.0 × RMSE | 0.1653 | 14.82 | 0.2206 | 4.28 |
The results show that our method maintains relatively stable mesh accuracy under mild reference perturbations, even when the perturbed reference is used for both selection and refinement. At 0.1 × RMSE, CD increases by approximately 0.5% for (0.1341 → 0.1348) and 0.4% for (0.1579 → 0.1585). At 0.25 × RMSE, where geometric deformations become visually noticeable, CD at increases only slightly from 0.1341 to 0.1357.
Under stronger perturbations, performance degradation becomes more pronounced, particularly at . As the perturbed reference deviates from the original G1–G4 candidates, fewer regions may satisfy the relative-depth-gain threshold, leading to fewer finer Gaussians being selected. Consistent with this, we observed a substantial decrease in selected G4 Gaussians as the perturbation magnitude increased. At 1.0 × RMSE, mesh size decreases from 9.16 to 4.28 MB at , accompanied by an increase in CD from 0.1579 to 0.2206. Thus, the accuracy degradation should be considered together with the substantial change in mesh complexity, rather than interpreted solely as degradation at a fixed mesh budget.
Overall, these results indicate that our method is relatively robust to mild reference-depth errors, while stronger perturbations can affect both Gaussian selection and final mesh accuracy. These findings further characterize the reference-quality limitation discussed in Appendix J.
2. Relationship Between Depth Gain and Mesh Complexity
We acknowledge that our relative-depth-gain criterion does not explicitly account for the mesh-complexity cost of individual Gaussian replacements. Instead, the threshold controls the extent of finer-Gaussian selection and the resulting geometry–mesh-size trade-off. Incorporating mesh-complexity cost directly into the selection criterion is a potential direction for future work, as already discussed in Appendix K.
W1 & Q1. Independent Contribution of Multi-Budget Composition
We thank the reviewer for raising this important concern. We agree that isolating the contribution of multi-budget composition from the subsequent Gaussian optimization is essential.
To address this, we extended the matched-optimization experiment in Table 12 to Gaussian Wrapping and GGGS, in addition to MILo. Specifically, we compare direct extraction from G4 and our composed representations, both with and without identical 2K Gaussian optimization.
Experimental setup. The following results are averaged over five scenes from the DeMapGS dataset (Book, Buddha, Bust, Cat, and Tree), following the same evaluation protocol as our main experiments. ✓ and ✗ indicate whether the identical 2K Gaussian optimization is applied or not, respectively.
Even without the 2K optimization, our composites produce smaller meshes with lower CD than G4 across all three backbones. These improvements remain after applying identical optimization to both G4 and Ours. In particular, for GGGS, composition reduces CD from 0.1180 to 0.1153 before optimization. After identical 2K optimization, Ours achieves a lower CD (0.1116 vs. 0.1132) with a smaller mesh (82.10 vs. 83.24 MB). These results demonstrate that multi-budget composition contributes to the geometry–mesh-size trade-off independently of the final Gaussian optimization, although the improvements at γ=0.2 are relatively modest.
As shown in Appendix B (Table 6) on NeRF Synthetic, our composites retain most G4 Gaussians at γ=0.2, consistent with the relatively small improvements over G4. At higher thresholds, Gaussians from different budgets are more substantially mixed, making the contribution of multi-budget composition more apparent.
To demonstrate this, we additionally compare our results at γ=0.6 against the same G4 baseline with identical 2K optimization.
For Gaussian Wrapping, Ours (γ=0.6) reduces mesh size by 15.3% (10.46 to 8.855 MB), with only a 0.0008 increase in CD (0.1544 to 0.1552). For GGGS, Ours (γ=0.6) achieves a 29.0% reduction in mesh size (83.24 to 59.07 MB), while CD increases only slightly from 0.1132 to 0.1137 (approximately 0.44%).
Overall, these results demonstrate that multi-budget composition provides improvements beyond those achieved by Gaussian optimization alone. While the improvements are modest at γ=0.2, composition enables more substantial mesh-size reductions with only minor changes in geometric accuracy at γ=0.6.