- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
ReVar3R estimates uncertainty from repeated predictions under input perturbations, using robust similarity alignment before computing per-point variance. The paper derives a distance-dependent variance term induced by scale and rotation changes and validates it through simulations and real-data experiments. The label-free core outperforms built-in confidence in 11 of 18 model–dataset conditions; fusion with weights fitted on held-out labels, including the built-in signal, increases this to 15.
Critical strengths
1. Clear analysis of gauge contamination in perturbation variance. The paper distinguishes predictive variation from apparent changes caused by scale, rotation, and translation. Its theoretical decomposition and testable distance-dependent predictions provide a clear account of this confound.
2. Applicability across frozen reconstruction models. The core estimator operates only on output point maps, requiring neither network modification nor retraining. Experiments on VGGT, π3, and MASt3R support its applicability across architectures.
3. Extensive ablations and transparent reporting of limitations. The paper examines alignment scope, reference selection, perturbation families, and sample count. It also distinguishes label-free estimation from supervised fusion and reports failures involving systematic bias, cross-domain calibration, and novel-view synthesis.
Critical weaknesses
1. Limited evidence of practical relevance and downstream benefits
The paper could better explain how unreliable 3D points affect practical systems and which problems improved reliability estimation can address. Point filtering closely reflects the selective prediction behavior measured by AUSE, while the novel-view synthesis experiment shows no improvement. Evaluation on representative tasks such as multi-view fusion, surface reconstruction, or localization would strengthen the evidence of practical utility.
2. Substantial inference overhead and an unclear cost–benefit trade-off
ReVar3R reportedly incurs approximately ten times the inference cost of a single-pass uncertainty head, but whether its benefits justify this overhead remains unclear. The cost reporting also needs clarification, including nine forward passes in the main protocol versus approximately ten to eleven in the cost table, and latency reported per set versus per pair. Comparisons under matched workloads and fixed computational budgets would better establish the efficiency–performance trade-off.
3. Limited independent scene coverage
The distance-effect experiment includes 30 view-sets from only eight scenes, while the Trust3R comparison covers only one KITTI sequence and two TUM sequences. View-sets from the same scene are correlated, so additional view-sets do not substitute for broader independent scene coverage. More independent scenes and scene-level statistical analyses would strengthen the generalization claims.
4. Inconsistent cross-domain performance and unclear applicability
ReVar3R performs well on KITTI, but its AUSE on the expanded ETH3D evaluation is 0.667, compared with 0.585 for built-in confidence, and magnitude calibration transfers poorly across domains. The estimated contamination strength also shows little correlation with alignment gains, providing limited guidance on when the method is likely to help. The paper would benefit from clearer applicability criteria and guidance on choosing between ReVar3R and built-in confidence without target-domain labels.
5. Predictive stability does not necessarily indicate geometric correctness
Alignment reduces variance caused by coordinate-frame changes, but the remaining variance need not reliably reflect geometric error. Appendix D.6 shows that increasing the fraction of stably biased points from 0 to 0.6 reduces the Spearman correlation between variance and error from +0.39 to −0.67, indicating that consistently incorrect predictions can receive low uncertainty scores. Quantifying the prevalence and impact of such errors in real scenes would better establish the limits of the proposed reliability measure.
Questions for authors
All questions are detailed in the weaknesses above.
4 comments
W3: independent scenes. We agree, and the problem was larger than stated: our main results came from only 12 independent scenes. We redid both experiments you name, and our main comparison, on 157 view-sets per model from 70 independent units (Appendix D.2; 64 units for the Trust3R comparison), each unit counting once.
1. Against built-in confidence (18 conditions): EQ is clearly better in 15, worse in 1 and unclear in 2; LW in 13 and never worse; Core alone in 9 and worse in 1, never on DTU or KITTI.
2. The distance test (you noted 30 view-sets from 8 scenes; Appendix B, Table 3 and Figure 4). For each view-set, the Spearman correlation between the frame-motion part of the variance, , and ; the theory predicts .
| Model | Image sets with | Median | Datasets where the interval is above 0 |
|---|---|---|---|
| VGGT | 146/157 | +0.61 | 6/6 |
| π³ | 153/157 | +0.76 | 6/6 |
| MASt3R | 146/157 | +0.45 | 6/6 |
The effect holds on average in every dataset for all three models (the paper had tested VGGT only). Our "positive in 30/30 view-sets" does not hold: 26 of 471 view-sets show no positive trend, most often DTU objects (12 of 26).
3. Against Trust3R (you noted 1 KITTI drive and 2 TUM sequences; Appendix D.6, Table 23), both at 224 px on identical images and points, after checking that both pipelines reproduce their stored AUSE from our submission exactly on a fixed ETH3D listing. EQ's AUSE minus Trust3R's, averaged over units:
| Dataset | Units | Difference [95% interval] | Units where ours is better |
|---|---|---|---|
| DTU | 30 | −0.233 [−0.274, −0.193] | 30 |
| KITTI | 9 | −0.089 [−0.116, −0.062] | 9 |
| 7-Scenes | 7 | −0.031 [−0.099, +0.020] | 5 |
| ETH3D | 13 | −0.002 [−0.064, +0.046] | 4 |
| TUM | 5 | +0.085 [+0.038, +0.134] | 0 |
Counting each unit once, ours is clearly better on DTU and KITTI, Trust3R on TUM, and neither on 7-Scenes or ETH3D. Pooled over all points, Trust3R leads on 7-Scenes, TUM and ETH3D (ETH3D: 0.498 vs 0.654), because pooled AUSE also rewards putting whole high-error scenes first; we report both. At 224 px, EQ is also clearly better than MASt3R's built-in confidence on all five datasets.
W4: uneven results across datasets, and when to use the method without labels.
ETH3D. Our paper's 0.667 vs 0.585 for built-in came from 9 scenes, because our copy of ETH3D was incomplete. On all 13 scenes, Core beats built-in confidence for all three models:
| Model | Core minus built-in, per-unit AUSE | Scenes where ours is better | p |
|---|---|---|---|
| VGGT | −0.167 | 10 of 13 | 0.012 |
| π³ | −0.132 | 11 of 13 | 0.008 |
| MASt3R | −0.084 | 10 of 13 | 0.036 |
EQ is clearly better on ETH3D for all three models too, including the paper's own setting (MASt3R at 224 px: lower than built-in by 0.137 [0.035, 0.246] per unit, 10 of 13 scenes; pooled 0.654 against 0.801).
Calibration does not carry over. Median for EQ is 0.002 with calibration data from the same images, 0.118 from an unseen scene and 0.382 from another dataset (all values in our reply to frTA, W2). Given the same labelled data, Trust3R's calibration transfers better (on the 64-unit, 224 px Trust3R comparison: 0.094 against 0.103 for EQ on unseen scenes; Table 25), and it needs no labels for an error size. Sorting points, our main use, needs no labelled fusion data.
Deciding without labels. We fixed three label-free signals in advance (Appendix D.5, Table 22) and rank-correlated each with the gain over built-in confidence across the 18 conditions (values for Core, EQ and LW; negative means a larger signal goes with a larger gain): share of the spread that alignment removes −0.05, +0.21, +0.16 (unrelated to the gain, as you observed); agreement of the two perturbation types −0.38, −0.43, −0.48; agreement with built-in confidence −0.29, −0.04, −0.22. None is reliable enough to decide on its own, and the paper no longer says alignment helps most where the frame moves. EQ is our fixed default, but no label-free rule tells when it will beat built-in confidence.
W5: being stable is not the same as being right. We agree. With the 10% of points with the largest error, the share of in a score's "confident" half (0.5 is chance) is On the benchmark (Appendix D.10, Table 31) the median share is 0.13 for EQ against 0.25 for built-in confidence, and EQ is lower in 17 of 18 conditions, but no score finds every stable error. In the 12 conditions with stored 3D points, a median 98.5% of points have an error more than 3 times their perturbation spread: repeated predictions often agree even when wrong. Our score sorts points; it is not an error bar, and the paper says so.
Presentation. The configurations are named Core, EQ and LW; Table 6 separates what needs labelled data from what does not; exact definitions are in Appendix D.1, with a pointer from Section 5.
Thank you for the substantial additional experiments and clarifications. The expanded scene coverage, corrected cost analysis, and transparent discussion of limitations strengthen the paper. While concerns about practical benefits and generalization remain, the response meaningfully addresses my main concerns, and I am raising my rating.
In short. We agree with your main points and changed the paper: (1) per-view filtering improves only modestly and merging views does not, and the paper says so; (2) our cost numbers were inconsistent and are re-measured; (3) the main results now rest on 70 independent scene groups instead of 12 scenes; (4) the ETH3D loss came from an incomplete dataset copy, and on all 13 scenes Core and EQ are clearly better than built-in confidence for all three models; (5) stable errors remain a limitation, now measured on real scenes.
W1: downstream use.
W2: cost. You are right that our reporting was inconsistent: the "about 10–11 passes" counted the shared run more than once, and the "about 9.9×" divided a time per set of 5 images by Trust3R's 0.919 s per image pair (our new measurement: 0.17 s per pair). We withdraw both. Our method uses 9 model runs (1 + 4 + 4). New timings (Appendix D.8, Table 27; same GPU, the same ten 5-view sets, median of 3 synchronized repeats):
About 70% of the time is the 8 extra runs; alignment takes 5 to 10%. At 224 px on the same sets Trust3R takes 0.66 s, so ours costs about 8.5 times more, the price of needing no trained head per model. At an equal number of runs, EQ is never worse than spending all runs on one perturbation type and clearly better in 3 to 5 of 6 conditions (reply to mWSG, Q5); a 5-run EQ costs about 6 times one run (estimated from stage timings).
W3 is answered in the next comment.