paper-with-me

홈 › Papers

From Pairs to Sequences: Track-Aware Policy Gradients for Keypoint Detection

2026-02-24 · Yepeng Liu, Hao Li, Liwen Yang, Fangzhen Li, Xudi Ge, Yuliang Gu, kuang Gao, Bing Wang, Guang Chen, Hangjun Ye, Yongchao Xu arxiv

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 \textbf{Tra}ck-\textbf{q}uality (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 (SOTA) keypoint detection and description methods.The code will be available at https://github.com/xiaomi-research/traqpoint.

📄 PDF Abstract BibTeX arXiv:2602.20630

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningKeypoint Detection3D ReconstructionPose Estimation

Similar Papers 제목 키워드 기반

Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning

2025-10-01 · Luckeciano C. Melo, Alessandro Abate, Yarin Gal arxiv

Reinforcement Learning, particularly through policy gradient methods, has played a central role in enabling reasoning capabilities of Large Language Models. However, the optimization stability of policy gradients in this…

Stochastic OptimizationReinforcement Learning

Not All Preferences Are Created Equal: Stability-Aware and Gradient-Efficient Alignment for Reasoning Models

2026-02-01 · Hui Wu, Hengyi Cai, Jinman Zhao, Xinran Chen 외 arxiv

Preference-based alignment is pivotal for training large reasoning models; however, standard methods like Direct Preference Optimization (DPO) typically treat all preference pairs uniformly, overlooking the evolving util…

Mathematical Reasoning

Diffusion Policy with Bayesian Expert Selection for Active Multi-Target Tracking

2026-04-03 · Haotian Xiang, Qin Lu, Yaakov Bar-Shalom arxiv

Active multi-target tracking requires a mobile robot to balance exploration for undetected targets with exploitation of uncertain tracked ones. Diffusion policies have emerged as a powerful approach for capturing diverse…

Estimating Dynamic Flow Features in Groups of Tracked Objects

2024-08-29 · Tanner D. Harms, Steven L. Brunton, Beverley J. McKeon

Interpreting motion captured in image sequences is crucial for a wide range of computer vision applications. Typical estimation approaches include optical flow (OF), which approximates the apparent motion instantaneously…

Multiple Object TrackingObject TrackingOptical Flow Estimation

SoftTreeMax: Policy Gradient with Tree Search

2022-09-28 · Gal Dalal, Assaf Hallak, Shie Mannor, Gal Chechik

Policy-gradient methods are widely used for learning control policies. They can be easily distributed to multiple workers and reach state-of-the-art results in many domains. Unfortunately, they exhibit large variance and…

Policy Gradient Methods