Abstract: Accurate 3D reconstruction from a single RGB image remains a challenging task in computer vision, especially in industrial applications such as quality inspection and virtual assembly, where existing methods still struggle with complex occlusions and multi-object interactions. This paper proposes a single-view 3D reconstruction method that integrates a channel attention mechanism with residual convolutional networks to enhance reconstruction accuracy and robustness in complex scenarios. The proposed method adopts an encode-decoder framework. The encoder incorporates an improved channel attention module to strengthen feature extraction in local regions and occluded areas, while the decoder predicts sub-voxel grid displacements based on back-projection rays to recover fine-grained structures. Experimental results on the ShapeNet synthetic dataset demonstrate that the proposed method achieves a mean intersection over union (mIoU) of 62.4% in single-object reconstruction at 128³ resolution, outperforming CoReNet by 3.3%. For multi-object scenarios, it reaches an mIoU of 48.2%, surpassing CoReNet by 4.3%. In severely occluded scenarios (>50% occlusion), the mIoU improves by 4.6%, confirming the robustness of the proposed approach. According to these analysis, the proposed method exhibits significant advantages in fine-detail reconstruction and multi-object interaction modeling, providing a high-precision solution for 3D reconstruction in complex industrial environments.