几何-光度事件式三维高斯光线追踪
Geometric-Photometric Event-based 3D Gaussian Ray Tracing
将事件式 3DGS 的渲染解耦为逐事件深度光线追踪与基于扭曲事件图像的快照式辐射渲染两条分支，使稀疏事件的高时序信息能被细粒度利用；这一「几何/光度分离 + 光线追踪」思路可迁移到其他事件相机或稀疏观测下的三维重建与新视角合成工作。
原文依据 decouple the rendering into two branches: event-by-event geometry (depth) rendering and snapshot-based radiance (intensity) rendering
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论事件相机相比传统帧式相机具有更高的时序分辨率，因而适用于运动与结构估计。然而，基于事件的 3D 高斯泼溅（3DGS）方法如何利用稀疏事件的细粒度时序信息此前尚不明确。本文提出 GPERT 框架，用以解决基于事件的 3DGS 中精度与时序分辨率之间的权衡问题。我们的核心思想是将渲染解耦为两条分支：借助光线追踪与扭曲事件图像，分别进行逐事件的几何（深度）渲染和基于快照的辐射（强度）渲染。大量评估表明，本方法在真实世界数据集上达到最优性能，在合成数据集上具有竞争力。此外，所提方法无需先验信息（如预训练图像重建模型）或基于 COLMAP 的初始化，在事件选取数量上更灵活，并能在快速训练下于场景边缘获得锐利重建。我们希望本工作能加深对事件稀疏性在三维重建中作用的理解。https://github.com/e3ai/gpert
英文原文摘要 1190 字符
Event cameras offer a high temporal resolution over traditional frame-based cameras, which makes them suitable for motion and structure estimation. However, it has been unclear how event-based 3D Gaussian Splatting (3DGS) approaches could leverage fine-grained temporal information of sparse events. This work proposes GPERT, a framework to address the trade-off between accuracy and temporal resolution in event-based 3DGS. Our key idea is to decouple the rendering into two branches: event-by-event geometry (depth) rendering and snapshot-based radiance (intensity) rendering, by using ray-tracing and the image of warped events. The extensive evaluation shows that our method achieves state-of-the-art performance on the real world datasets and competitive performance on the synthetic dataset. Also, the proposed method works with out prior information (e.g., pretrained image reconstruction models) or COLMAP-based initialization, is more flexible in the event selection number, and achieves sharp reconstruction on scene edges with fast training time. We hope that this work deepens our understanding of the sparse nature of events for 3D reconstruction. https://github.com/e3ai/gpert