无需物理先验，端到端实现事件相机3D重建
Towards End-to-End Neuromorphic Event-based 3D Object Reconstruction Without Physical Priors
- 提出新型事件表示增强边缘特征，提升学习效果
- 相比基线方法，重建准确率提升54.6%
- 适合追求高效、无先验依赖重建的科研与工业场景
类脑摄像头（事件相机）是异步亮度变化传感器，能无运动模糊地捕捉极高速运动，在极端环境下的3D重建中极具潜力。然而，当前基于单目事件相机的3D重建研究有限，多数方法依赖物理先验并采用复杂的多步骤流程。本文提出一种端到端的密集体素3D重建方法，无需估计物理先验。通过引入新型事件表示以增强边缘特征，使所提特征增强模型学习更有效。此外，我们提出最优二值化阈值选择原则，以阈值优化后获得的最佳重建结果为基准，为后续研究提供参考。实验表明，该方法相较基线显著提升54.6%的重建准确率。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。