中文标题#
面向端到端神经形态事件的 3D 物体重建无需物理先验
英文标题#
Towards End-to-End Neuromorphic Event-based 3D Object Reconstruction Without Physical Priors
中文摘要#
神经形态相机，也称为事件相机，是异步亮度变化传感器，可以在不产生运动模糊的情况下捕捉极快的运动，这使得它们在极端环境中的三维重建中特别有前景。 然而，使用单目神经形态相机进行三维重建的现有研究有限，大多数方法依赖于估计物理先验，并采用复杂的多步骤流程。 在本工作中，我们提出了一种使用神经形态相机进行密集体素三维重建的端到端方法，消除了估计物理先验的需要。 我们的方法结合了一种新的事件表示来增强边缘特征，使提出的特征增强模型能够更有效地学习。 此外，我们引入了最优二值化阈值选择原则作为未来相关工作的指导，使用通过阈值优化获得的最佳重建结果作为基准。 与基线方法相比，我们的方法在重建精度上提高了 54.6%。
英文摘要#
Neuromorphic cameras, also known as event cameras, are asynchronous brightness-change sensors that can capture extremely fast motion without suffering from motion blur, making them particularly promising for 3D reconstruction in extreme environments. However, existing research on 3D reconstruction using monocular neuromorphic cameras is limited, and most of the methods rely on estimating physical priors and employ complex multi-step pipelines. In this work, we propose an end-to-end method for dense voxel 3D reconstruction using neuromorphic cameras that eliminates the need to estimate physical priors. Our method incorporates a novel event representation to enhance edge features, enabling the proposed feature-enhancement model to learn more effectively. Additionally, we introduced Optimal Binarization Threshold Selection Principle as a guideline for future related work, using the optimal reconstruction results achieved with threshold optimization as the benchmark. Our method achieves a 54.6% improvement in reconstruction accuracy compared to the baseline method.
PDF 获取#
抖音扫码查看更多精彩内容