This study presents a vision-based closed-loop tracking system designed specifcally for robotic laser beam welding of curved and closed square butt joints. The proposed system is compared against 11 existing solutions reported in the literature, which employ various sensor principles for the same application. The system employs a non-contact, non-intrusive machine vision approach, seamlessly integrated into the laser beam welding head to mitigate challenges associated with sensor forerun. Key features include an of-axis LED illumination, an optical flter, and a movable actuator, facilitating real-time image processing and closed-loop control during the welding process. Experimental validation was conducted on stainless-steel plates with complex closed square butt joints. The system achieved a mean absolute joint-to-beam ofset of 0.14 mm across four test cases, with a maximum ofset of 0.85 mm, demonstrating its robustness and precision. Comparative analysis underscores the proposed method’s advantages, showcasing its potential for industrial applications in laser beam welding of geometrically challenging joints.