The authors analyze and improve the DeDoDe keypoint detector, which follows the "detect, don't describe" approach. They identify several key issues with the original DeDoDe detector and propose a series of improvements:
Clustering issue: The DeDoDe detector tends to produce clusters of keypoints in distinct regions, leading to underdetection in other regions. The authors address this by performing non-max suppression on the target distribution during training.
Training efficiency: The authors find that the original long training of DeDoDe is detrimental to performance on downstream tasks like relative pose estimation. They propose a much shorter training schedule of 10,000 image pairs, which significantly improves performance while reducing training time.
Data augmentation: The DeDoDe detector is sensitive to large rotations. The authors address this by including 90-degree rotations and horizontal flips in the data augmentation.
Evaluation: The decoupled nature of the DeDoDe detector makes evaluation of downstream usefulness problematic. The authors fix this by matching the keypoints with a pretrained dense matcher (RoMa) and evaluating two-view pose estimates.
The authors integrate all these improvements into their proposed DeDoDe v2 detector and evaluate it on the MegaDepth-1500 and IMC2022 benchmarks. DeDoDe v2 significantly outperforms the original DeDoDe detector, setting new state-of-the-art results.
翻譯成其他語言
從原文內容
arxiv.org
深入探究