- Rating
- 3
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes MarginalGS, a two-stage framework for native high-resolution 3D Gaussian reconstruction that addresses region-wise representation imbalance. Stage 1 fits a low-resolution 3DGS and computes high-resolution residuals; Stage 2 performs a posteriori capacity allocation using a per-primitive deficit score, then applies a one-time 1-to-4 decomposition and assigns either full 3D or restricted covariance support for the children based on an Eckart–Young–Mirsky error criterion and reliability gates, followed by patch-based native-resolution refinement. On four 6K real-world datasets, MarginalGS reports the best SSIM and ROI PSNR on all datasets, competitive full-image PSNR, and the lowest total training memory among compared methods.
Critical strengths
-
Introduces a clear formalization of representation-conditioned capacity allocation via a marginal-value objective and KKT-based intuition, and operationalizes it with a per-primitive a posteriori “deficit score” that fuses residuals, opacity, scale, and multi-view visibility.
-
Integrates anchor-guided high-resolution patch rendering to supervise selected regions at native sampling density without full-image rasterization, effectively decoupling supervision fidelity from training memory overhead.
Critical weaknesses
- The EYM-based criterion ensures bounded covariance approximation error under rank-2 restriction, but does not directly control rendering or photometric error; failure modes on nonplanar or weakly textured regions are mitigated heuristically (stabilization loss, reliability gates) rather than theoretically addressed.
Questions for authors
Could you provide more detail and intuition on the collapsed-support stabilization objective Lcol (its exact form and gradients) and how it prevents degenerate updates during Stage 2? Any failure modes you observed when varying λsh, λop, λsc, or λori?
4 comments
Additional Validation on Public Outdoor Scenes
Beyond the stabilization clarifications, we added native-5K evaluation on three public Mip-NeRF 360 scenes: bicycle, stump, and garden. Their outdoor textures, boundaries, and 3D structures complement our four self-collected indoor datasets. All methods use the same inputs, view splits, and 10K-iteration budget; MarginalGS retains shared hyperparameters across scenes. MarginalGS achieves the highest PSNR, SSIM, and ROI PSNR on all three among the compared methods.
Table 3 reports the following results. PSNR and ROI PSNR are in dB.
| Scene | Method | PSNR ↑ | SSIM ↑ | ROI PSNR ↑ |
|---|---|---|---|---|
| bicycle | 3DGS | 23.231 | 0.634 | 26.173 |
| LODGS | 23.825 | 0.652 | 24.202 | |
| Mip-Splatting | 23.855 | 0.681 | 25.837 | |
| Analytic Splatting | 22.887 | 0.623 | 26.536 | |
| Multi-scale Gaussian | 23.090 | 0.627 | 25.612 | |
| MarginalGS (Ours) | 24.423 | 0.721 | 28.560 | |
| stump | 3DGS | 25.389 | 0.733 | 20.620 |
| LODGS | 25.882 | 0.744 | 20.543 | |
| Mip-Splatting | 26.722 | 0.775 | 21.060 | |
| Analytic Splatting | 25.193 | 0.729 | 21.172 | |
| Multi-scale Gaussian | 25.195 | 0.729 | 21.142 | |
| MarginalGS (Ours) | 26.888 | 0.789 | 24.062 | |
| garden | 3DGS | 25.614 | 0.754 | 21.719 |
| LODGS | 25.347 | 0.725 | 21.991 | |
| Mip-Splatting | 26.201 | 0.790 | 22.395 | |
| Analytic Splatting | 25.470 | 0.741 | 21.686 | |
| Multi-scale Gaussian | 25.350 | 0.741 | 21.406 | |
| MarginalGS (Ours) | 26.320 | 0.808 | 23.166 |
ROI PSNR improves over each scene's strongest baseline by 2.024, 2.890, and 0.771 dB, respectively. Together with the full-image improvements, these results support better overall fidelity and fine-detail recovery on public outdoor scenes.
Complete-pipeline time includes residual scanning/scoring and is normalized by 10K iterations (Appendix Table 10):
| Scene | Fastest compared baseline | Baseline (s/iter) ↓ | MarginalGS (Ours) (s/iter) ↓ |
|---|---|---|---|
| bicycle | 3DGS | 0.447 | 0.312 |
| stump | 3DGS | 0.375 | 0.228 |
| garden | 3DGS | 0.480 | 0.276 |
These quality gains accompany the lowest reported complete-pipeline time on all three scenes under this protocol.
Revision locations: Sec. 4, Datasets (lines 319–322); Sec. 4.1, outdoor-results paragraph (p. 8); Table 3 and Fig. 4 (p. 9); Appendix A.6, ROI examples (pp. 23–24); Appendix Table 10 (p. 23).
We hope this expanded public-benchmark evidence strengthens your assessment of the paper's contribution and experimental completeness.
Additional Clarifications on Evaluation Design and Attribution
Dear Reviewer,
We would like to draw your attention to additional clarifications in the revised manuscript.
Appendix A.2 (lines 1040–1055) now explains why the four native-6K indoor scenes were constructed around fine-detail recovery, including resolution testing charts (Fig. 11), how they complement the public outdoor evaluation, and why component analysis is concentrated on 4base4r while the added outdoor experiments assess transfer with unchanged hyperparameters.
Appendix A.1.3 (lines 829–843) further clarifies the assignment ablation: eligibility rules assess support suitability, the budget cap limits allocation within the eligible set, and stabilization regulates subsequent updates. This makes the attribution to the complete assignment policy explicit.
We hope these additions, together with our earlier responses and supplementary experiments, help address your concerns. We would appreciate any remaining questions and your updated assessment when convenient. Thank you for your time and consideration.
Thank you for the careful rebuttal about expanded explanation of the objective and gradients, clarified mechanism, and the robustness. The additional results on public outdoor scenes seem promising. I will maintain my score.
Collapsed-Support Stabilization and Weight Sensitivity
Thank you for your suggestion. We have expanded the paper in three respects: the objective and its gradients, the Stage-II stabilization mechanism, and weight sensitivity.
1. Expanded explanation of the objective and gradients.
Sec. 3.4 (lines 303–309) now explains the four terms: the SH term suppresses view-dependent appearance variation, the opacity term encourages transparent or opaque states, the scale term promotes localized support, and the orientation term encourages consistency between neighboring support directions.
Appendix A.1.6 (lines 898–986) provides the exact definitions, participating primitive sets, weight schedule, and gradients with respect to SH coefficients, opacity logits, log-scales, and rotation parameters. It also clarifies which discrete selections are not differentiated.
2. Clarified mechanism for preserving thin support and controlling Stage-II updates.
We now distinguish the losses from the explicit safeguards. After the default Adam update, the smallest log-scale is reset to −15 to prevent support-thickness drift. Before the update, geometric-gradient damping and SH contraction work alongside the auxiliary losses to regulate geometric and appearance changes, while the remaining geometric parameters stay trainable.
This explains support preservation through concrete update operations, rather than attributing it solely to Lcol. The complete update order is specified in Appendix A.1.6 (lines 987–1009).
3. Added weight-sensitivity results and observed failure modes.
We conduct one-weight-at-a-time perturbations on 4base4r, keeping the other settings unchanged. The results are:
Values are PSNR in dB; OOM denotes memory exhaustion. Both scheduled orientation weights are scaled together. The default row repeats the same existing result across columns.
The observed failures were memory exhaustion under the tested non-default SH weights, strengthened opacity regularization, and weakened orientation schedules; the strongest scale penalty reduced reconstruction accuracy. The default completes with the highest PSNR, supporting retention of the current weights. Detailed settings and analysis appear in Appendix A.1.6 (lines 1010–1033 and Table 5), with a summary in Sec. 4.2 (lines 520–525).