- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
The paper proposes FixTrust-GS, a method for weighting repaired-view supervision in sparse-view 3D Gaussian Splatting. It trains auxiliary reconstructions on complementary subsets of captured images and checks whether repaired pixels agree with these reconstructions better than the original renders. The resulting pixel-wise weights are used during continued 3DGS optimization. Evaluation covers three datasets, two pretrained repair models, and three training-view budgets.
Critical strengths
-
The paper addresses a relevant problem. Repaired images can introduce scene-inconsistent content, so deciding which edits to trust is important. Comparing a repair against the original render, rather than judging its absolute disagreement alone, is a reasonable approach. The method also works without modifying the pretrained repair model.
-
The reliability diagnostics provide useful supporting evidence. Figure 4 examines whether higher weights correspond to actual repair improvements against ground truth. This is more informative than reporting reconstruction metrics alone and suggests that the weighting captures some useful signal.
Critical weaknesses
- The added value of the proposed weighting is not convincingly established.
The experiments mainly compare Train-only and different supervision weights within the same repair pipeline. These are useful controls, but they do not establish an advantage over the existing reliability-aware repair methods discussed in Section 2.
Several improvements become quite small against stronger scalar settings in the appendix. For example, Table 17 reports 17.34 versus 17.29 dB on Deep Blending with nine training views and 48 repair views, compared with a global weight of 0.1. Meanwhile, LPIPS worsens from 0.571 to 0.576, and the proposed method uses slightly more Gaussians. On LLFF with nine training views, both repair backends remain below Train-only in PSNR. These results do not demonstrate a consistent quality advantage.
The extensive parameter sweeps also do not replace a robustness evaluation: only one training seed is reported. Furthermore, fixed-HW weighting changes both the spatial allocation and the overall strength of repair supervision. Figure 4’s equal-mass diagnostic is useful, but it is a post-hoc analysis rather than an end-to-end reconstruction control. Comparisons against per-image mean weights or spatially shuffled maps would help establish whether precise pixel selection is responsible for the gains.
- The qualitative presentation does not adequately substantiate the artifact-reduction claims.
Figure 4 and the appendix comparisons pack many small images into dense grids. Labels and numerical overlays compete with the image content, while enlarged crops and clearly identified artifact regions are missing. At the presented scale, it is difficult to determine which structures or textures are improved relative to the baselines. Adding more thumbnails does not resolve this problem. For a paper about rejecting harmful repairs, the qualitative evidence should make the corrected and preserved details directly inspectable; the current figures do not do this convincingly.
Questions for authors
-
Do the final reconstruction gains remain when comparing against per-image mean weights and spatially shuffled maps with the same total weight? This would help separate spatial reliability estimation from simply weakening repair supervision.
-
How stable are the reported margins across random seeds and captured-view selections? Please also clarify how the default settings were selected and whether a separate validation set was used.
-
How does the method compare with an existing reliability-aware repair integration method under matched conditions? Such a comparison would materially affect my assessment of the contribution.
3 comments
Comment 2 — Random seeds and default settings
Q2. Random seeds, captured views, and default settings
Optimization seeds. We repeated the full pipeline with seeds 42/43/44 at Train 9, Repair 48, , on Bicycle, Bonsai, Counter, Garden, Kitchen, Room, and Stump. Training/test identities remain fixed; the main and auxiliary models are retrained and repaired supervision is regenerated for each seed. Table 2 reports the mean and sample standard deviation of per-seed scene averages, including the full scalar sweep. Our mean PSNR, SSIM, and LPIPS improve over every tested scalar weight for both repair models. This supports robustness in the tested setting, not statistical significance for every original dataset or view budget.
Table 2. Mean sample standard deviation over seeds 42/43/44, Train 9, Repair 48, , on the stated Mip-NeRF 360 subset.
| Supervision | Difix3D — PSNR ↑ | Difix3D — SSIM ↑ | Difix3D — LPIPS ↓ | Diffusion Harmonizer — PSNR ↑ | Diffusion Harmonizer — SSIM ↑ | Diffusion Harmonizer — LPIPS ↓ |
|---|---|---|---|---|---|---|
| Train-only | 18.335 ± 0.081 | 0.5291 ± 0.0015 | 0.3306 ± 0.0021 | 18.325 ± 0.111 | 0.5286 ± 0.0020 | 0.3310 ± 0.0021 |
| Global 1.0 | 18.687 ± 0.054 | 0.5313 ± 0.0002 | 0.3478 ± 0.0014 | 19.108 ± 0.041 | 0.5414 ± 0.0005 | 0.3982 ± 0.0027 |
| Global 0.9 | 18.710 ± 0.031 | 0.5329 ± 0.0006 | 0.3477 ± 0.0010 | 19.111 ± 0.028 | 0.5424 ± 0.0003 | 0.3966 ± 0.0018 |
| Global 0.8 | 18.742 ± 0.040 | 0.5346 ± 0.0003 | 0.3477 ± 0.0010 | 19.128 ± 0.024 | 0.5435 ± 0.0003 | 0.3954 ± 0.0014 |
| Global 0.7 | 18.755 ± 0.047 | 0.5364 ± 0.0001 | 0.3480 ± 0.0011 | 19.140 ± 0.026 | 0.5447 ± 0.0006 | 0.3941 ± 0.0019 |
| Global 0.6 | 18.781 ± 0.036 | 0.5381 ± 0.0004 | 0.3483 ± 0.0009 | 19.163 ± 0.025 | 0.5466 ± 0.0004 | 0.3916 ± 0.0019 |
| Global 0.5 | 18.807 ± 0.043 | 0.5403 ± 0.0003 | 0.3488 ± 0.0008 | 19.182 ± 0.034 | 0.5484 ± 0.0004 | 0.3890 ± 0.0024 |
| Global 0.4 | 18.832 ± 0.034 | 0.5428 ± 0.0005 | 0.3487 ± 0.0010 | 19.204 ± 0.032 | 0.5508 ± 0.0005 | 0.3850 ± 0.0018 |
| Global 0.3 | 18.855 ± 0.058 | 0.5453 ± 0.0006 | 0.3494 ± 0.0007 | 19.224 ± 0.037 | 0.5537 ± 0.0002 | 0.3802 ± 0.0013 |
| Global 0.2 | 18.902 ± 0.046 | 0.5488 ± 0.0003 | 0.3487 ± 0.0012 | 19.229 ± 0.012 | 0.5569 ± 0.0008 | 0.3737 ± 0.0019 |
| Global 0.1 | 18.906 ± 0.041 | 0.5510 ± 0.0007 | 0.3496 ± 0.0006 | 19.214 ± 0.019 | 0.5598 ± 0.0006 | 0.3645 ± 0.0018 |
| FixTrust-GS | 19.163 ± 0.066 | 0.5573 ± 0.0010 | 0.3430 ± 0.0015 | 19.317 ± 0.032 | 0.5631 ± 0.0003 | 0.3596 ± 0.0012 |
Default settings and validation. The reported experiments use , fixed-HW normalization, and 48 repair views as common defaults. We selected based on the completed fold-count ablation and its quality–cost trade-off. Fixed-HW retains the full-image denominator so that reliable area affects a repair's total contribution. The supplementary seed and view-selection comparisons hold these settings fixed. The available experiment records define training, repair, and test splits, but do not document a separate validation set. We therefore do not present these defaults as independently validation-selected. We will explicitly document the selection procedure and distinguish the reported ablations from independent validation.
Comment 3 — Captured-view selection and HAD comparison
Q2. Captured-view selection (continued)
Captured-view selection. We evaluated the original subset and two alternatives selected by random-start, pose-based farthest-point sampling (selection seeds 137/271), with optimization seed 42 fixed. The test images, non-test candidate pool, Train 9 and Repair 48 counts remain fixed. The remaining non-test cameras become repair views, so repair-camera identities can change with the training subset. No image-quality or test metric selects the subsets. All models and repairs are regenerated for each alternative, and competing methods use matched inputs within each subset.
Table 3. Captured-view selection on Mip-NeRF 360, Train 9, Repair 48, . Each row averages the same full scene set. The test images and optimization seed are fixed; repair-camera identities may change with the training subset.
Original captured subset
| Supervision | Difix3D — PSNR ↑ | Difix3D — SSIM ↑ | Difix3D — LPIPS ↓ | Diffusion Harmonizer — PSNR ↑ | Diffusion Harmonizer — SSIM ↑ | Diffusion Harmonizer — LPIPS ↓ |
|---|---|---|---|---|---|---|
| Train-only | 17.210 | 0.4776 | 0.3830 | 17.217 | 0.4778 | 0.3823 |
| Global 1.0 | 17.615 | 0.4824 | 0.4006 | 18.016 | 0.4931 | 0.4542 |
| Global 0.5 | 17.732 | 0.4910 | 0.4029 | 18.081 | 0.4996 | 0.4454 |
| Global 0.3 | 17.779 | 0.4957 | 0.4050 | 18.123 | 0.5045 | 0.4370 |
| FixTrust-GS | 18.058 | 0.5066 | 0.4020 | 18.195 | 0.5127 | 0.4179 |
Alternative subset: selection seed 137
| Supervision | Difix3D — PSNR ↑ | Difix3D — SSIM ↑ | Difix3D — LPIPS ↓ | Diffusion Harmonizer — PSNR ↑ | Diffusion Harmonizer — SSIM ↑ | Diffusion Harmonizer — LPIPS ↓ |
|---|---|---|---|---|---|---|
| Train-only | 17.395 | 0.4829 | 0.3778 | 17.395 | 0.4829 | 0.3778 |
| Global 1.0 | 17.841 | 0.4879 | 0.3981 | 18.227 | 0.4968 | 0.4510 |
| Global 0.5 | 17.921 | 0.4962 | 0.4008 | 18.294 | 0.5036 | 0.4425 |
| Global 0.3 | 17.993 | 0.5009 | 0.4025 | 18.317 | 0.5078 | 0.4350 |
| FixTrust-GS | 18.262 | 0.5113 | 0.3995 | 18.436 | 0.5172 | 0.4158 |
Alternative subset: selection seed 271
| Supervision | Difix3D — PSNR ↑ | Difix3D — SSIM ↑ | Difix3D — LPIPS ↓ | Diffusion Harmonizer — PSNR ↑ | Diffusion Harmonizer — SSIM ↑ | Diffusion Harmonizer — LPIPS ↓ |
|---|---|---|---|---|---|---|
| Train-only | 16.758 | 0.4678 | 0.3955 | 16.758 | 0.4678 | 0.3955 |
| Global 1.0 | 17.231 | 0.4732 | 0.4122 | 17.648 | 0.4850 | 0.4623 |
| Global 0.5 | 17.326 | 0.4813 | 0.4149 | 17.703 | 0.4910 | 0.4559 |
| Global 0.3 | 17.373 | 0.4860 | 0.4165 | 17.741 | 0.4958 | 0.4477 |
| FixTrust-GS | 17.648 | 0.4972 | 0.4135 | 17.789 | 0.5036 | 0.4289 |
Table 3 shows higher average PSNR and SSIM than the tested scalar weights for both models under all three selections. Relative to Global 0.3, the PSNR margins range from 0.269–0.279 dB for Difix3D and 0.047–0.119 dB for Diffusion Harmonizer. LPIPS improves over Global 0.3 in each selection, but Difix3D remains worse than Global 1.0 in LPIPS. Thus the margins vary with the captured views, and the gains are not uniform across metrics. We will report both robustness protocols and results with these limitations.
Q3. Matched reliability-aware comparison
We evaluated HAD's released reliability scorer with its preprocessing, threshold 0.9, and three nearest captured-view references. The repaired images, camera splits, saved checkpoint, loss, and continuation schedule are identical; only the supervision weights differ. This compares reliability components within a common pipeline, not the complete HAD reconstruction system. Table 4 shows higher PSNR and SSIM and lower LPIPS for our method with both repair models. We will include this matched comparison and clearly describe its scope.
Table 4. Matched HAD comparison on Mip-NeRF 360, Train 9, Repair 48. HAD uses its reliability scorer in the common training pipeline.
| Supervision | Difix3D — PSNR ↑ | Difix3D — SSIM ↑ | Difix3D — LPIPS ↓ | Diffusion Harmonizer — PSNR ↑ | Diffusion Harmonizer — SSIM ↑ | Diffusion Harmonizer — LPIPS ↓ |
|---|---|---|---|---|---|---|
| HAD reliability mask | 17.819 | 0.4935 | 0.4038 | 18.008 | 0.4966 | 0.4425 |
| FixTrust-GS | 18.058 | 0.5066 | 0.4020 | 18.195 | 0.5127 | 0.4179 |
Comment 1 — Spatial weighting and qualitative evidence
We thank the reviewer for the detailed assessment of spatial weighting, robustness, and qualitative evidence. The requested controls help distinguish pixel selection from reduced supervision strength, and we report them alongside the presentation revisions.
In result tables, bold marks the best reported value per metric within each comparison, including ties.
W1. Added value and robustness
We agree that the original results do not establish a consistent advantage across all settings. In the cited Deep Blending setting, the PSNR gain over Global 0.1 is only 0.05 dB, while LPIPS and Gaussian count are worse. Both repair models also remain below Train-only in PSNR on LLFF with nine training views. We will state these trade-offs explicitly and qualify the abstract, main-results discussion, and conclusion rather than imply universal improvements.
We have completed the requested comparisons on Mip-NeRF 360, Train 9, Repair 48. Against per-image mean and shuffled weights, the PSNR gains are 0.260/0.259 dB for Difix3D and 0.088/0.094 dB for Diffusion Harmonizer, with improved mean SSIM and LPIPS (Question 1, Table 1). We also report three optimization seeds and alternative captured-view subsets (Question 2), and a matched HAD comparison with gains of 0.239/0.187 dB (Question 3). We will add these results and their evaluation scope to the paper.
W2. Inspectable qualitative evidence
The dense thumbnail grids did not make the relevant details sufficiently inspectable. We have revised Figure 4 and Appendix C.4 to show fewer, larger examples, with magnified crops beside the corresponding full images. Colored boxes mark identical regions across methods, and captions identify the structures and textures to compare. Method labels are placed outside the image content; reported PSNR is computed on the full image, not the selected crop. The comparisons retain Train-only, scalar-weight baselines, and our method. These changes make the claimed differences directly inspectable rather than relying on additional thumbnails.
Q1. Equal-total-weight reconstruction controls
Yes, the average reconstruction gains remain against both requested controls. For each repaired image, we replace its map either by its own mean weight or by a spatial permutation of its weights. Both preserve its total weight; shuffling also preserves its histogram. All methods resume the same checkpoint with the same repairs, cameras, fixed-HW denominator, and optimization schedule. These are end-to-end reconstruction runs, distinct from Figure 4's post-hoc diagnostic. Table 1 supports a benefit from spatial allocation beyond simply reducing total supervision weight. Our Gaussian counts are slightly higher than these controls, so this comparison supports improved reconstruction quality, not an additional reduction in model size.
Table 1. End-to-end equal-weight controls on Mip-NeRF 360, Train 9, Repair 48, K=3. Each control preserves the total weight within each repaired image.
Difix3D
Diffusion Harmonizer