AI 中文总结
针对自监督单目深度估计模型在嵌入式环境中能耗高、兼容性差的问题，提出基于XiNet算子块的轻量架构XiDepth，在KITTI数据集上仅0.8M参数即达最优性能，树莓派测试显示其FLOPs降40%、能耗降35%。
AI 中文摘要
自监督单目深度估计因减少对昂贵深度传感器的依赖，已成为为计算受限设备设计轻量高效模型的极具吸引力的解决方案。该方法无需真实标注，且利用单目相机设置的简洁性，可实现高性价比的数据采集，并广泛适用于计算机视觉、机器人学等领域。其关键挑战在于构建资源高效的神经网络，同时不损害整体性能。现有最优模型通常采用深度卷积和注意力机制，但这些功能往往带来高能耗，且在嵌入式环境中存在兼容性问题。为解决此问题，我们提出XiDepth，一种基于XiNet算子块的轻量架构，旨在增强特征提取能力，同时保持低计算复杂度和低能耗。在KITTI数据集上，XiDepth仅用0.8M参数就达到了最优性能；在树莓派4（Raspberry Pi 4）上的测试进一步证实其适用于实际嵌入式应用，与领先方法相比，其浮点运算量（FLOPs）减少了40%，能耗降低了35%。
英文摘要
Self-supervised monocular depth estimation has emerged as an appealing solution to design lightweight and effective models for deployment on computationally constrained devices due to its reduced reliance on expensive depth sensors. By eliminating the need for ground-truth annotations and leveraging the simplicity of monocular camera setups, this approach facilitates cost-effective data collection and broad applicability across fields such as computer vision and robotics. A critical challenge is achieving resource-efficient neural networks without compromising the overall performance. State-of-the-art models generally adopt depth-wise convolutions and attention mechanisms; however, these functions often incur high energy costs and face compatibility issues in embedded environments. To address this, we propose XiDepth, a lightweight architecture based on the XiNet operator block, designed to enhance feature extraction while maintaining low computational complexity and energy demand. On the KITTI dataset, XiDepth achieves state-of-the-art performance with only 0.8M parameters. Tests on a Raspberry Pi 4 further confirm its suitability for real-world embedded applications, reducing FLOPs by 40% and energy consumption by 35% compared to leading methods.
CommentsAccepted to IEEE AVSS 2026
