从图像对到序列：面向关键点检测的轨迹感知策略梯度
From Pairs to Sequences: Track-Aware Policy Gradients for Keypoint Detection
把关键点检测从图像对监督改为序列上的强化学习决策过程，用轨迹质量奖励驱动策略梯度，可直接用于 SfM/SLAM 前端特征点训练，提升长时序跟踪稳定性。
原文依据 we reframe keypoint detection as a sequential decision-making problem
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于关键点的匹配是现代三维视觉系统（如 Structure-from-Motion（SfM）与 SLAM）的基础组成部分。现有大多数基于学习的方法在图像对上训练，这一范式无法在具有挑战性的视角与光照变化下显式优化关键点在序列上的长期可跟踪性。本文将关键点检测重新表述为序列决策问题。我们提出 TraqPoint，一种新颖的端到端强化学习（RL）框架，旨在直接在图像序列上优化关键点的轨迹质量（Traq）。我们的核心创新是一种轨迹感知奖励机制，在策略梯度方法的引导下，联合促进关键点在多视图间的一致性与可区分性。在稀疏匹配基准（包括相对姿态估计与三维重建）上的大量评估表明，TraqPoint 显著优于一些最优的关键点检测与描述方法。代码将发布于 https://github.com/xiaomi-research/traqpoint。
英文原文摘要 1098 字符
Keypoint-based matching is a fundamental component of modern 3D vision systems, such as Structure-from-Motion (SfM) and SLAM. Most existing learning-based methods are trained on image pairs, a paradigm that fails to explicitly optimize for the long-term trackability of keypoints across sequences under challenging viewpoint and illumination changes. In this paper, we reframe keypoint detection as a sequential decision-making problem. We introduce TraqPoint, a novel, end-to-end Reinforcement Learning (RL) framework designed to optimize the Track-quality (Traq) of keypoints directly on image sequences. Our core innovation is a track-aware reward mechanism that jointly encourages the consistency and distinctiveness of keypoints across multiple views, guided by a policy gradient method. Extensive evaluations on sparse matching benchmarks, including relative pose estimation and 3D reconstruction, demonstrate that TraqPoint significantly outperforms some state-of-the-art keypoint detection and description methods. The code will be available at https://github.com/xiaomi-research/traqpoint.