Search papers, labs, and topics across Lattice.
This paper introduces Mesh-Aware Epipolar Matching (MAEM), a training-free framework for multi-view multi-person 3D pose estimation that leverages monocular 3D human mesh recovery as a frontend. MAEM addresses challenges in team sports scenarios, such as occlusions and appearance similarity, by employing a two-stage epipolar matching strategy based on the recovered mesh outputs. Experiments on multi-view basketball datasets demonstrate that MAEM outperforms existing training-free baselines and achieves competitive RGB-only performance, showcasing the effectiveness of dense mesh geometry for cross-view association.
Ditching training, MAEM leverages 3D mesh recovery to nail multi-view 3D pose estimation in crowded, confusing team sports scenes.
Multi-view multi-person 3D pose estimation in team sports scenarios remains challenging due to player occlusions, appearance similarity caused by team uniforms, and the scarcity of annotated multi-view data, all of which limit the effectiveness and generalization capability of learning-based methods. In contrast, the performance of training-free approaches is inherently constrained by the accuracy of 2D keypoint detection and the robustness of cross-view association. To address these challenges, we propose Mesh-Aware Epipolar Matching (MAEM), a training-free framework for multi-view multi-person 3D pose estimation. Our method employs a monocular 3D human mesh recovery model as the frontend and introduces a two-stage epipolar matching strategy based on the recovered mesh outputs. Specifically, the proposed framework combines disjoint-set-union-based clustering with per-joint triangulation to achieve robust cross-view association and accurate 3D pose reconstruction. Experiments on two public multi-view basketball datasets demonstrate that MAEM consistently outperforms existing training-free association baselines while achieving competitive RGB-only performance in both indoor and outdoor basketball scenarios. MAEM achieves MPJPE/PA-MPJPE scores of 59.8/40.7 mm on SportCenter EPFL and 74.0/51.8 mm on Human-M3 Basketball, highlighting the effectiveness of dense mesh geometry for cross-view association without requiring target-domain training or fine-tuning.
