IncEventGS：基于单一事件相机的无位姿高斯泼溅
IncEventGS: Pose-Free Gaussian Splatting from a Single Event Camera
AI总结：
提出IncEventGS，利用SLAM跟踪-建图范式，基于单一事件相机增量重建3D高斯泼溅场景，无需真实位姿，性能优于NeRF基线和事件视觉里程计方法。
摘要：
近年来，基于帧的相机（如RGB和RGB-D相机）的隐式神经表示和显式3D高斯泼溅（3D-GS）在新视图合成方面取得了显著进展。与基于帧的相机相比，一种新型的仿生视觉传感器——事件相机，在高时间分辨率、高动态范围、低功耗和低延迟方面展现出优势。由于其独特的异步和规则不规则的数据采集过程，目前将神经表示或3D高斯泼溅应用于事件相机的工作有限。在本工作中，我们提出了IncEventGS，一种基于单一事件相机的增量式3D高斯泼溅重建算法。为了增量地恢复3D场景表示，我们利用了传统SLAM流程的跟踪与建图范式。给定输入的事件流，跟踪器首先基于先前重建的3D-GS场景表示估计初始相机运动。随后，建图器根据跟踪器先前估计的运动轨迹，联合优化3D场景表示和相机运动。实验结果表明，即使在没有真实相机位姿的情况下，IncEventGS相比先前的基于NeRF的方法和其他相关基线也表现出更优的性能。此外，在相机运动估计方面，我们的方法相比最先进的事件视觉里程计方法也取得了更好的性能。代码公开于：https://github.com/wu-cvgl/IncEventGS。
英文摘要：
Implicit neural representation and explicit 3D Gaussian Splatting (3D-GS) for novel view synthesis have achieved remarkable progress with frame-based camera (e.g. RGB and RGB-D cameras) recently. Compared to frame-based camera, a novel type of bio-inspired visual sensor, i.e. event camera, has demonstrated advantages in high temporal resolution, high dynamic range, low power consumption and low latency. Due to its unique asynchronous and irregular data capturing process, limited work has been proposed to apply neural representation or 3D Gaussian splatting for an event camera. In this work, we present IncEventGS, an incremental 3D Gaussian Splatting reconstruction algorithm with a single event camera. To recover the 3D scene representation incrementally, we exploit the tracking and mapping paradigm of conventional SLAM pipelines for IncEventGS. Given the incoming event stream, the tracker firstly estimates an initial camera motion based on prior reconstructed 3D-GS scene representation. The mapper then jointly refines both the 3D scene representation and camera motion based on the previously estimated motion trajectory from the tracker. The experimental results demonstrate that IncEventGS delivers superior performance compared to prior NeRF-based methods and other related baselines, even we do not have the ground-truth camera poses. Furthermore, our method can also deliver better performance compared to state-of-the-art event visual odometry methods in terms of camera motion estimation. Code is publicly available at: https://github.com/wu-cvgl/IncEventGS.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
