Liu Jiaxuan, Wu Jingyi, Jing Ruiyang, Yu Han, Liu Jing, Song Liang
Academy for Engineering and Technology, Fudan University, Shanghai 200433, China.
Innovation Platform for Academicians of Hainan Province, Haikou 570228, China.
Sensors (Basel). 2025 Feb 28;25(5):1513. doi: 10.3390/s25051513.
In recent years, generating 3D human models from images has gained significant attention in 3D human reconstruction. However, deploying large neural network models in practical applications remains challenging, particularly on resource-constrained edge devices. This problem is primarily because large neural network models require significantly higher computational power, which imposes greater demands on hardware capabilities and inference time. To address this issue, we can optimize the network architecture to reduce the number of model parameters, thereby alleviating the heavy reliance on hardware resources. We propose a lightweight and efficient 3D human reconstruction model that balances reconstruction accuracy and computational cost. Specifically, our model integrates Dilated Convolutions and the Cross-Covariance Attention mechanism into its architecture to construct a lightweight generative network. This design effectively captures multi-scale information while significantly reducing model complexity. Additionally, we introduce an innovative loss function tailored to the geometric properties of normal maps. This loss function provides a more accurate measure of surface reconstruction quality and enhances the overall reconstruction performance. Experimental results show that, compared with existing methods, our approach reduces the number of training parameters by approximately 80% while maintaining the generated model's quality.
近年来，从图像生成3D人体模型在3D人体重建中受到了广泛关注。然而，在实际应用中部署大型神经网络模型仍然具有挑战性，特别是在资源受限的边缘设备上。这个问题主要是因为大型神经网络模型需要显著更高的计算能力，这对硬件能力和推理时间提出了更高的要求。为了解决这个问题，我们可以优化网络架构以减少模型参数的数量，从而减轻对硬件资源的严重依赖。我们提出了一种轻量级且高效的3D人体重建模型，该模型平衡了重建精度和计算成本。具体来说，我们的模型将空洞卷积和交叉协方差注意力机制集成到其架构中，以构建一个轻量级生成网络。这种设计有效地捕获了多尺度信息，同时显著降低了模型复杂性。此外，我们引入了一种针对法线贴图几何属性量身定制的创新损失函数。该损失函数提供了更准确的表面重建质量度量，并提高了整体重建性能。实验结果表明，与现有方法相比，我们的方法在保持生成模型质量的同时，将训练参数数量减少了约80%。
