自己運動補償によるイベントカメラからの単眼深度学習
Learning Monocular Depth from Events via Egomotion Compensation
イベントカメラのデータに物理的な運動補償の原理を組み込み、焦点の合い具合を手がかりに解釈可能な単眼深度推定を行うフレームワークを提案した。
著者: Haitao Meng, Chonghao Zhong, Sheng Tang, Lian JunJia, Wenwei Lin, Zhenshan Bing, Yi Chang, Gang Chen, Alois Knoll
分類: cs.CV, cs.LG, cs.RO
原文アブストラクト
Event cameras are neuromorphically inspired sensors that sparsely and asynchronously report brightness changes. Their unique characteristics of high temporal resolution, high dynamic range, and low power consumption make them well-suited for addressing challenges in monocular depth estimation (e.g., high-speed or low-lighting conditions). However, current existing methods primarily treat event streams as black-box learning systems without incorporating prior physical principles, thus becoming over-parameterized and failing to fully exploit the rich temporal information inherent in event camera data. To address this limitation, we incorporate physical motion principles to propose an interpretable monocular depth estimation framework, where the likelihood of various depth hypotheses is explicitly determined by the effect of motion compensation. To achieve this, we propose a Focus Cost Discrimination (FCD) module that measures the clarity of edges as an essential indicator of focus level and integrates spatial surroundings to facilitate cost estimation. Furthermore, we analyze the noise patterns within our framework and improve it with the newly introduced Inter-Hypotheses Cost Aggregation (IHCA) module, where the cost volume is refined through cost trend prediction and multi-scale cost consistency constraints. Extensive experiments on real-world and synthetic datasets demonstrate that our proposed framework outperforms cutting-edge methods by up to 10\% in terms of the absolute relative error metric, revealing superior performance in predicting accuracy.
