arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2205.01694cs.CV
收藏

端到端多视图特征匹配与可微位姿优化

End2End Multi-View Feature Matching with Differentiable Pose Optimization

Technical University of Munich(慕尼黑工业大学)

Barbara Roessle, Matthias Nießner

AI总结:

提出联合处理特征匹配与位姿优化的图注意力网络,利用可微位姿估计的梯度训练特征匹配以降低离群点权重,在多个数据集上显著提升位姿估计精度并大幅减少耗时。

摘要:

错误的特征匹配会对后续的相机位姿估计产生严重影响,并且通常需要额外的、耗时的措施(如RANSAC)来剔除离群点。我们的方法通过联合处理特征匹配和位姿优化来解决这一挑战。为此,我们提出了一种图注意力网络来预测图像对应关系以及置信度权重。生成的匹配在可微位姿估计中作为加权约束。利用位姿优化的梯度来训练特征匹配,自然地学会了降低离群点的权重,与SuperGlue相比,在ScanNet上将图像对的位姿估计提升了6.7%。同时,它将位姿估计时间减少了50%以上,并使RANSAC迭代变得不必要。此外,我们通过将图跨越多个帧来整合来自多个视图的信息,以一次性预测匹配。多视图匹配结合端到端训练,与SuperGlue相比,在Matterport3D上将位姿估计指标提升了18.5%。

英文摘要:

Erroneous feature matches have severe impact on subsequent camera pose estimation and often require additional, time-costly measures, like RANSAC, for outlier rejection. Our method tackles this challenge by addressing feature matching and pose optimization jointly. To this end, we propose a graph attention network to predict image correspondences along with confidence weights. The resulting matches serve as weighted constraints in a differentiable pose estimation. Training feature matching with gradients from pose optimization naturally learns to down-weight outliers and boosts pose estimation on image pairs compared to SuperGlue by 6.7% on ScanNet. At the same time, it reduces the pose estimation time by over 50% and renders RANSAC iterations unnecessary. Moreover, we integrate information from multiple views by spanning the graph across multiple frames to predict the matches all at once. Multi-view matching combined with end-to-end training improves the pose estimation metrics on Matterport3D by 18.5% compared to SuperGlue.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑