The paper introduces MF-MOS, a novel dual-branch model for LiDAR-based moving object segmentation (MOS) in autonomous driving. The primary focus is on capturing motion information from residual maps and integrating semantic features from range images. The model consists of a motion branch that processes residual maps to capture dynamic features and a semantic branch that uses range images to provide semantic guidance. A key contribution is the Strip Average Pooling Layer (SAPL), which is designed to handle the non-square alignment of residual and range images. Additionally, the 3D Spatial-Guided Information Enhancement Module (SIEM) refines the segmentation results by enhancing spatial information. Extensive experiments on the SemanticKITTI dataset demonstrate that MF-MOS achieves state-of-the-art performance, outperforming other methods by achieving an IoU of 76.7% on the leaderboard. The paper also includes ablation studies and qualitative analysis to validate the effectiveness of each component of the model.The paper introduces MF-MOS, a novel dual-branch model for LiDAR-based moving object segmentation (MOS) in autonomous driving. The primary focus is on capturing motion information from residual maps and integrating semantic features from range images. The model consists of a motion branch that processes residual maps to capture dynamic features and a semantic branch that uses range images to provide semantic guidance. A key contribution is the Strip Average Pooling Layer (SAPL), which is designed to handle the non-square alignment of residual and range images. Additionally, the 3D Spatial-Guided Information Enhancement Module (SIEM) refines the segmentation results by enhancing spatial information. Extensive experiments on the SemanticKITTI dataset demonstrate that MF-MOS achieves state-of-the-art performance, outperforming other methods by achieving an IoU of 76.7% on the leaderboard. The paper also includes ablation studies and qualitative analysis to validate the effectiveness of each component of the model.