GEVO：使用高斯法的内存高效单目视觉里程计
GEVO: Memory-Efficient Monocular Visual Odometry Using Gaussians
AI总结：
GEVO是一个基于GS的单目SLAM框架，通过从地图渲染而非存储图像，结合新的Gaussian初始化与优化技术，在保持地图保真度的同时将内存开销降至约58 MBs。
摘要：
使用单目相机构建高保真度的3D场景表示，能够为微型机器人、智能手机和AR/VR头显等移动设备带来广泛的应用。在这些设备上，内存容量通常有限，且内存访问往往主导计算能耗。尽管Gaussian Splatting（GS）允许对3D场景进行高保真重建，但当前基于GS的SLAM在内存使用上并不高效，因为需要存储大量过去的图像来重新训练Gaussians，以减少灾难性遗忘。这些图像所需的内存通常比地图本身高两个数量级，从而主导了总内存使用量。在本研究中，我们提出了GEVO，这是一个基于GS的单目SLAM框架，通过从现有地图中渲染（而非存储）图像，实现了与先前方法相当的保真度。我们提出了新颖的Gaussian初始化和优化技术，以消除地图中的伪影并延缓渲染图像随时间的质量退化。在多种环境中，GEVO实现了相当的地图保真度，同时将内存开销降至约58 MBs，比先前的工作最多低94倍。
英文摘要：
Constructing a high-fidelity representation of the 3D scene using a monocular camera can enable a wide range of applications on mobile devices, such as micro-robots, smartphones, and AR/VR headsets. On these devices, memory is often limited in capacity and its access often dominates the consumption of compute energy. Although Gaussian Splatting (GS) allows for high-fidelity reconstruction of 3D scenes, current GS-based SLAM is not memory efficient as a large number of past images is stored to retrain Gaussians for reducing catastrophic forgetting. These images often require two-orders-of-magnitude higher memory than the map itself and thus dominate the total memory usage. In this work, we present GEVO, a GS-based monocular SLAM framework that achieves comparable fidelity as prior methods by rendering (instead of storing) them from the existing map. Novel Gaussian initialization and optimization techniques are proposed to remove artifacts from the map and delay the degradation of the rendered images over time. Across a variety of environments, GEVO achieves comparable map fidelity while reducing the memory overhead to around 58 MBs, which is up to 94x lower than prior works.
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。
