arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.01596cs.CV
收藏

无需对应点的双视图几何评分

Two-View Geometry Scoring Without Correspondences

Niantic(Niantic公司);University of Oxford(牛津大学);University College London(伦敦大学学院)

Axel Barroso-Laguna, Eric Brachmann, Victor Adrian Prisacariu, Gabriel J. Brostow, Daniyar Turmukhambetov

AI总结:

本文提出 FSNet,通过对极注意力直接评估图像对与候选基础矩阵的位姿误差,无需稀疏对应点,并可嵌入 RANSAC,在少匹配或不可靠匹配场景及与 MAGSAC++ 结合时取得先进性能。

摘要:

双视图几何的相机位姿估计传统上依赖 RANSAC。通常,大量图像对应点会产生一个候选假设池,随后对这些假设进行评分以找出胜出模型。内点数量通常被视为“共识”的可靠指标。我们考察了这种评分启发式方法,发现它在某些情况下会偏向令人失望的模型。作为补救措施,我们提出了 Fundamental Scoring Network(FSNet,基础评分网络),它为一对重叠图像以及任意候选基础矩阵推断一个评分。该方法不依赖稀疏对应点,而是通过对极注意力机制体现双视图几何模型,该机制预测两幅图像的位姿误差。FSNet 可以被整合进传统 RANSAC 循环中。我们在室内和室外数据集上评估了 FSNet 的基础矩阵和本质矩阵估计性能,并证实 FSNet 能够在对应点很少或不可靠的图像对中成功识别良好位姿。此外,我们表明,将 FSNet 与 MAGSAC++ 评分方法简单结合即可取得最先进的结果。

英文摘要:

Camera pose estimation for two-view geometry traditionally relies on RANSAC. Normally, a multitude of image correspondences leads to a pool of proposed hypotheses, which are then scored to find a winning model. The inlier count is generally regarded as a reliable indicator of "consensus". We examine this scoring heuristic, and find that it favors disappointing models under certain circumstances. As a remedy, we propose the Fundamental Scoring Network (FSNet), which infers a score for a pair of overlapping images and any proposed fundamental matrix. It does not rely on sparse correspondences, but rather embodies a two-view geometry model through an epipolar attention mechanism that predicts the pose error of the two images. FSNet can be incorporated into traditional RANSAC loops. We evaluate FSNet on fundamental and essential matrix estimation on indoor and outdoor datasets, and establish that FSNet can successfully identify good poses for pairs of images with few or unreliable correspondences. Besides, we show that naively combining FSNet with MAGSAC++ scoring approach achieves state of the art results.

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。

↑