- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 3
Read review
Paper summary
The paper proposes Residual Quantile Regression (RQR) for learned two-view correspondence pruning. It augments thresholded inlier classification with pinball-supervised quantiles of transformed epipolar residuals. Two training-only integrations use these predictions either to guide native correspondence scores or to supervise shared features. An inference-time variant, RQR-F, retains the quantile descriptor to condition features and modify weights for weighted eight-point estimation. Evaluation includes paired comparisons across six pruning architectures, relative-pose estimation, homography transfer, cross-domain and cross-feature testing, and a fixed-host RQR-F ablation. The results demonstrate benefits in several settings, while also showing substantial dependence on the host architecture, supervision placement, and geometric estimator.
Critical strengths
The paper identifies a meaningful limitation of thresholded inlier labels and shows that additional residual supervision can benefit an existing pruning pipeline. In particular, BCLNet’s reported weighted AUC@5 improves from 33.36 to 37.13. Since the auxiliary prediction heads are removed at inference, this improvement comes without additional inference modules. This is a useful practical result, although it primarily supports the value of residual supervision rather than establishing the specific advantage of multiple quantiles.
Critical weaknesses
-
The quantile-specific contribution is not established. In Table 4, Huber outperforms three-quantile RQR under the matched all-interface comparison, while the stronger final-interface RQR result lacks corresponding Huber/Laplace controls. Table 3 also bundles quantile prediction, supervision, and weighting. These experiments do not isolate the benefit of multiple quantiles from continuous residual supervision, supervision placement, or additional weighting.
-
The smaller improvements lack repeatability support. Each configuration uses a single training run. The paired bootstrap measures test-pair variability, not training variability, leaving the modest gains on several hosts and the incremental prompting benefit insufficiently substantiated.
-
The presentation is substantially below the standard expected of a research paper. The method section is unnecessarily opaque: key definitions are delayed or incomplete, and three materially different implementations are interwoven without a coherent account of their data flow, objectives, and gradient paths. The prose repeatedly relies on abstract, formulaic descriptions without providing the concrete explanations needed to understand the computation. Readers must reconstruct the actual pipelines by piecing together scattered passages across the main text and appendices.
Questions for authors
-
Quantile-specific contribution: How does final-interface RQR compare with Huber and Laplace supervision under matched training schedules and validation-selection budgets? For RQR-F, how does quantile supervision alone compare with adding the proposed inference-time weighting? These comparisons would clarify whether multiple quantiles provide benefits beyond continuous residual supervision and its placement.
-
Repeatability: How consistent are the reported improvements across independent training runs? Please report means and variability for representative host comparisons and the RQR-F ablation, particularly whether the smaller gains and the incremental prompting benefit persist across seeds.
-
Method specification: Can the authors provide a consolidated algorithm or diagram for each of the three integrations, explicitly identifying the residual transformation, prediction heads, loss terms, gradient paths—including detached connections—and components retained at inference? Please also resolve the delayed or incomplete symbol definitions so that each pipeline can be understood and reconstructed unambiguously.
6 comments
K2. Separating residual supervision from inference weighting
Thank you for pointing out that the original ablation combined quantile supervision and weighting.
Concern. Does quantile supervision alone help, and what does using the predicted gaps at inference contribute beyond that supervision?
Response. We separate the trained supervision-only configuration from an intervention on the weights of the same trained model. The latter gives the direct test of whether predicted gaps are useful during geometric estimation.
In Table B.2, each Off/On pair shares identical trained parameters and differs only in the explicit gap penalties:
| Feature prompt | Gap weighting at inference | Weighted AUC@5 / 10 / 20 |
|---|---|---|
| No | Off | 38.13 / 59.50 / 75.32 |
| No | On | 38.90 / 59.98 / 75.63 |
| Yes | Off | 38.55 / 59.73 / 75.74 |
| Yes | On | 39.15 / 60.12 / 75.94 |
Using the gaps improves weighted AUC at all three tolerances with either prompt configuration. The paired weighted-gain intervals are positive (Section 4.5 and Appendix B.1). This establishes an inference benefit within each evaluated model without attributing it to another training run.
Table 6 and Table B.5 provide the separate training controls:
| Without feature prompt | Weighted AUC@5 / 10 / 20 | RANSAC AUC@5 / 10 / 20 |
|---|---|---|
| Supervision only | 37.98 / 59.33 / 75.40 | 35.79 / 56.10 / 72.83 |
| Detached gap gradients | 38.90 / 59.66 / 75.61 | 36.34 / 56.56 / 73.26 |
| Joint training | 38.90 / 59.98 / 75.63 | 35.61 / 55.98 / 72.82 |
Supervision only removes all gap penalties during both training and inference and omits the prompt. Pinball therefore acts through shared correspondence features. This is a different model from the first Off row above, which was trained with gap weighting.
The independently trained controls are not a matched-budget decomposition. The same-model intervention isolates the contribution of gap weighting at inference.
Quantile supervision shapes shared features, and the learned gaps also carry useful information for weighted fitting. Table 3 still reports their combined addition, with the smaller prompt increment interpreted separately.
Revision. Sections 4.4-4.5 and Tables 5-6 (pp. 9-10) distinguish these comparisons. Appendix B.1/Table B.2 (p. 15) documents the same-model intervention; Appendix B.4/Table B.5 (pp. 16-17) defines the training controls and reports RANSAC results.
K3. Training variability and the size of the reported gains
Thank you for distinguishing repeatability across training runs from uncertainty over test pairs.
Concern. Do the smaller gains and the incremental feature-prompt benefit persist across independent seeds, with means and variability?
Response. Our paired native/RQR comparisons build on the corresponding public implementations, using the same correspondence inputs and evaluation settings within each pair. Each configuration is represented by one training run. The reported intervals quantify test-pair variability conditional on those trained models.
Table B.1 gives these representative paired AUC-point changes with 95% image-pair intervals:
| RQR minus native | Weighted AUC@5 gain [95% CI] | Weighted AUC@10 gain [95% CI] | Weighted AUC@20 gain [95% CI] |
|---|---|---|---|
| PointCN | +0.30 [-0.26, +0.86] | +1.19 [+0.50, +1.87] | +1.25 [+0.64, +1.88] |
| BCLNet | +3.77 [+2.98, +4.56] | +2.79 [+2.11, +3.47] | +1.39 [+0.89, +1.88] |
| GeoMoE | +0.67 [-0.07, +1.40] | +0.29 [-0.32, +0.89] | +0.05 [-0.38, +0.48] |
BCLNet's weighted gain has positive intervals at every tolerance. PointCN has positive intervals at 10 and 20 degrees, while its 5-degree interval includes zero. OANet, CLNet, DeMatch++ and GeoMoE have weighted intervals that include zero at all three thresholds. These are different levels of support within the evaluated test set.
The original RQR-F ablation remains in Table 3:
| RQR-F configuration | Weighted AUC@5 | Weighted AUC@10 |
|---|---|---|
| Base | 37.63 | 59.05 |
| Quantile supervision and weighting | 38.90 | 59.98 |
| With feature prompt | 39.15 | 60.12 |
Appendix B.1 states that the additional prompt gains have paired intervals that include zero. We therefore describe the prompt result as an observed increment, not an independently established repeatability gain. The same-model weighting intervention in Table 5 addresses a separate question: whether this trained model benefits from the gap penalties at inference.
Our study focuses on residual-supervision objectives and inference-time weighting across architectures and estimators. We will investigate repeatability across independent training seeds in future work.
Revision. Section 4.1 (p. 6), Section 4.4 (p. 9), and Appendix B/Table B.1 (pp. 14-15) identify what the intervals measure. The prompt interpretation is stated in Section 4.4 and Appendix B.1.
K1. Quantile targets at the final prediction stage
Thank you for identifying supervision placement as a confound in the original residual-target comparison.
Concern. How does final-stage RQR compare with Huber and Laplace when the training schedule and validation-selection budget are matched?
Response. RQR has higher weighted AUC@5 than both matched final-stage controls, with positive paired intervals for both differences. The final-stage comparison uses the same BCLNet architecture, supervision location, three-output head capacity, initialization, classification and geometric objectives, and residual-loss coefficient (0.25). The objectives share the same training schedule and validation-selection budget. All auxiliary heads are removed at inference.
Table 4 and Appendix Table B.4 report the following pose AUCs (%):
Appendix B.3 quantifies the weighted differences in AUC points:
This comparison changes the residual objective while holding its location and capacity fixed. Huber applies Smooth L1 to three predictions of the same scalar target; Laplace learns a location and positive scale; RQR supervises three ordered levels. Thus the result supports a benefit of the quantile objective beyond adding continuous supervision at this location. It does not identify quantile asymmetry alone as the cause.
The all-stage results in Table 4 remain: Huber and Laplace outperform three-quantile RQR there. At the final stage, RQR improves tight-angle weighted pose accuracy; at 20 degrees it matches Laplace to the reported precision. The corresponding RANSAC difference intervals include zero. The evidence therefore ties the quantile advantage to supervision placement and the geometric estimator.
Revision. Section 4.4 and Table 4 (p. 9) now separate all-stage and final-stage supervision. Appendix B.3/Table B.4 (p. 16) specifies the matched objectives and intervals; the conclusion (p. 10) limits the advantage to tighter weighted-pose tolerances.