In this study, we propose an autonomous underwater vehicle (AUV)-based multi-directional scanning method of underwater objects using forward scan sonar (FSS). Recently, a method was developed that can generate a 3-D point cloud of an underwater object using FSS. However, the data comprised sparse and noisy characteristics that made it difficult for 3-D recognition. Another limitation was the absence of back and side surface information of an object. These limitations degraded the results of the 3-D reconstruction. We propose a multi-directional scanning strategy to improve the 3-D point cloud and reconstruction results where the AUV determines the direction of the next scan by analyzing the 3-D data of the object until the scanning is complete. This enables adaptive scanning based on the shape of the target object while reducing the amount of scanning time. Based on the scanning strategy, a polygonal approximation method for real-time 3-D reconstruction is developed to process scanned data groups of the 3-D point cloud. This process can efficiently handle multiple 3-D point cloud data for real-time operation and reduce its uncertainty. To verify the performance of our proposed method, simulations were performed with various objects and conditions. In addition, experiments were conducted in an indoor water tank, and the results were compared with the simulation results. Field experiments were conducted to verify the proposed method for more diverse environments and objects.