通过关键点空间一致性检测姿态估计失败，提升下游任务可靠性。
Detecting Pose Estimation Failures via Keypoint Self-Consistency
- 设计几何特征捕捉关键点间自洽性，如距离、重投影与渲染一致性。
- 基于这些特征的逻辑回归模型准确识别姿态估计失败，优于依赖置信度的方法。
- 适合需要高可靠性的工业视觉应用，尤其在关键点预测不精准时。
姿态估计通常先预测图像中物体的关键点，再用透视n点（PnP）算法计算物体相对于相机的旋转和平移。虽然旋转保持物体形状不变，但现有基于关键点的方法常独立预测各关键点，忽略此几何约束。不精确的关键点预测不仅降低姿态估计精度，还影响下游任务的可靠性。本文探索仅通过分析2D关键点间的空间位置关系，能否识别姿态估计失败。提出一组手工设计的几何特征，包括成对距离、重投影一致性、渲染一致性及掩码一致性。尽管方法简单，但基于这些特征训练的逻辑回归分类器能有效检测姿态估计失败，性能优于仅依赖关键点不确定性的置信度方法（如置信区间关键点预测）。
原文摘要 · Abstract (English)
One common approach to pose estimation involves predicting object keypoints in an image, followed by using Perspective-n-Point algorithms to compute the object's rotation and translation relative to the camera. While rotations preserve object shapes, this property is often neglected in keypoint-based pose estimation methods, where keypoints are typically predicted independently from each other. As imprecise keypoint predictions negatively affects pose estimation accuracy, it also limits its reliability in downstream tasks. In this work, we explore whether such inaccurate pose estimates can be identified by simply examining spatial locations between 2D keypoints. We propose a set of hand-crafted geometric features that capture the self-consistency of keypoint predictions, including pairwise distances, reprojection consistency, as well as render and mask consistency. Despite its simplicity, a logistic regression classifier trained on these features reliably detects pose estimation failures, outperforming confidence-based approaches like conformal keypoint predictions that rely solely on keypoint uncertainty.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。