This paper introduces a novel framework for 3D pose estimation in combat sports. Utilizing a sparse multi-camera setup, our approach employs a computer vision-based tracker to extract 2D pose predictions from each camera view, enforcing consistent tracking targets across views with epipolar constraints and long-term video object segmentation. Through a top-down transformer-based approach, we ensure high-quality 2D pose extraction. We estimate the 3D position via weighted triangulation, spline fitting. By employing kinematic optimization and multi-person physics-based trajectory refinement, we achieve state-of-the-art accuracy and robustness under challenging conditions such as occlusion, rapid movements and close interactions. Experimental validation on diverse datasets, including a custom dataset featuring elite boxers, underscores the effectiveness of our approach. Additionally, we contribute a valuable video datasets to advance research in multi-person tracking, in particular for combat sports.