XiDepth: 自己教師あり単眼深度推定のための軽量かつ効率的なネットワーク
XiDepth: a Lightweight and Efficient Network for Self-supervised Monocular Depth Estimation
XiNet演算子ブロックに基づく軽量アーキテクチャXiDepthを提案し、KITTIデータセットで0.8Mパラメータで最先端性能を達成、Raspberry Pi 4での実装でFLOPsと消費電力を大幅削減した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Elena Izzo, Riccardo Toniolo, Lamberto Ballan
分類: cs.CV
原文アブストラクト
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.