NeurIPS 2020

RSKDD-Net: Random Sample-based Keypoint Detector and Descriptor


Meta Review

The initial scores for this paper were: 6: Marginally above the acceptance threshold. 6: Marginally above the acceptance threshold. 8: Top 50% of accepted NeurIPS papers. A very good submission; a clear accept. While the reviewers are overall positive, they raised several concerns regarding: Technical details of the method. Metrics used for evaluation. More thorough ablations. Computational time. The authors provide a rebuttal, which addresses most of the weak points. In the post-rebuttal discussion, and considering the rebuttal, R1 upgrades their score from 6 to 7. The final scores are 6, 7, 8. The AC is convinced by the positive arguments of the reviewers and recommends Accept. The authors are strongly encouraged to take into account all reviewers' feedback and final recommendations when preparing the final version.