用事件相机实现头戴视角下动态背景中的3D手部建模
EventEgoHands: Event-based Egocentric 3D Hand Mesh Reconstruction
- 通过手部分割模块过滤动态背景噪声，提升事件相机鲁棒性
- 在N-HOT3D数据集上将MPJPE降低4.5厘米以上（提升43%）
- 适合需要低光或高速运动场景的交互系统研究者
3D手部网格重建对人机交互与AR/VR应用至关重要。传统方法依赖RGB或深度相机，但在弱光环境和运动模糊下表现不佳。事件相机具备高动态范围和高时间分辨率，近年受到关注。但其易受背景噪声和相机运动干扰，现有研究多局限于静态背景与固定相机。本文提出EventEgoHands，一种面向头戴视角的事件相机3D手部建模新方法。引入手部分割模块，有效抑制动态背景事件干扰。在N-HOT3D数据集上评估，相较基线显著提升性能，平均关键点误差（MPJPE）降低超过4.5厘米（相对改善43%）。
原文摘要 · Abstract (English)
Reconstructing 3D hand mesh is challenging but an important task for human-computer interaction and AR/VR applications. In particular, RGB and/or depth cameras have been widely used in this task. However, methods using these conventional cameras face challenges in low-light environments and during motion blur. Thus, to address these limitations, event cameras have been attracting attention in recent years for their high dynamic range and high temporal resolution. Despite their advantages, event cameras are sensitive to background noise or camera motion, which has limited existing studies to static backgrounds and fixed cameras. In this study, we propose EventEgoHands, a novel method for event-based 3D hand mesh reconstruction in an egocentric view. Our approach introduces a Hand Segmentation Module that extracts hand regions, effectively mitigating the influence of dynamic background events. We evaluated our approach and demonstrated its effectiveness on the N-HOT3D dataset, improving MPJPE by approximately more than 4.5 cm (43%).
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。