- Rating
- 3(+1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes R²,a point cloud registration framework based on shared geometric regression.Via a single forward pass,the framework maps sampled anchor points from the two input point clouds into a shared canonical coordinate space.It then establishes point correspondences following the mutual nearest-neighbor rule and solves for the rigid transformation using SVD.For loss design,the method combines coordinate regression loss and cross-view geometric coupling loss to constrain the predicted coordinates and local geometric relations.
Critical strengths
(1)The idea of mapping two point clouds into a shared canonical space is inspiring, and it achieves a favorable trade-off between registration accuracy and computational overhead. (2)Ablation studies demonstrate that both cross-view geometric supervision and intermediate-layer supervision effectively boost registration performance, with particularly prominent gains under low-overlap scenarios.
Critical weaknesses
(1)While the ablation results validate the effectiveness of the proposed supervision designs,the intrinsic advantage brought by the shared canonical space itself remains unclear.Additional experiments are required to justify this claim. (2)Table 3 shows that replacing SVD with RANSAC provides only a small improvement in overall recall.However, the robustness of the default solver remains insufficiently characterized.Reporting correspondence inlier ratios and comparing the two solvers across overlap levels would help clarify when MNN+SVD is reliable and when robust estimation remains beneficial.
Questions for authors
(1)What is the correlation between the rigidity score adopted in TTA and registration success?Is it possible that predictions satisfying rigidity constraints individually yet yielding wrong relative alignment can still obtain low rigidity scores? (2)What criteria were used to set the triggering and stopping thresholds for TTA?Were these thresholds tuned solely on the validation set?How robust is the registration performance with respect to variations in these threshold values?
Warm Thank You and Quick Summary of Tables 1, 2, and 3
Dear Reviewer hBXF,
Thank you again for your helpful review! Since our earlier reply above was quite detailed, we wanted to leave a short 3-point summary here for your easy reference, showing how our unified results highlight the strengths of
R²:R²leads across Recall, RRE, and RTE at high speed): As you noted in Strengths,R²achieves the highest recall on both 3DMatch and 3DLoMatch. Once REGTR is evaluated under the exact same error rule (mean vs. mean, or median vs. median),R²not only beats REGTR on every metric (+16.71% recall on 3DLoMatch), but actually achieves the lowest RRE and lowest (or tied-lowest) RTE across all methods in Table 1, while running in one59 mspass (1.7x to 20x faster than other high-recall methods at 98-1,428 ms).5° / 200 cm), 99.8% recall already means succeeding on 554 out of all 555 test pairs. While baselines with slightly smaller RE/TE (e.g.,0.23° / 4.9 cmvs. our0.24° / 7.7 cm) rely on RANSAC or multi-step pose refinement,R²reaches this ceiling in one simple SVD step with zero extra refinement.R²'s core strength): BothMNN+SVDandMNN+RANSACin Table 3 are two versions of our ownR². In 3D registration, conventional methods fail badly withoutRANSACbecause of wrong matches. The fact that our defaultR² (MNN+SVD)gets almost the exact same high accuracy (95.28% / 81.63%) asR² (MNN+RANSAC)(95.39% / 82.17%, random sampling) proves how clean and accurateR²'s one-shot predictions already are, while users can freely choose either version in practice.Thank you very much for your effort and sharp observations, which helped make these strengths much clearer in our revised paper. If these clarifications address your concerns, we would be sincerely grateful if you could kindly consider updating your score, and we wish you all the best!
Warm regards,
The Authors