用实时生成新视角，让视觉导航算法验证更快更准。
Enabling Robust, Real-Time Verification of Vision-Based Navigation through View Synthesis
- 通过实时合成新视角，扩展稀疏数据集生成连续轨迹。
- 提出新姿态距离度量，提升视图合成精度与稳定性。
- 适合做自动驾驶、机器人视觉导航的算法验证者。
本文提出VISY-REVE：一种用于验证视觉导航图像处理算法的新流程。传统方法如合成渲染或机器人实验平台采集存在部署困难和运行缓慢的问题。为此，我们提出在实时中通过合成新视角来扩充图像数据集，从而从稀疏的已有数据集中生成连续轨迹，适用于开放或闭环场景。此外，我们引入一种新的相机姿态间距离度量——瞄准偏差距离（Boresight Deviation Distance），其相比现有指标更适配视图合成任务。基于该度量，发展出一种提升图像数据集密度的方法。
原文摘要 · Abstract (English)
This work introduces VISY-REVE: a novel pipeline to validate image processing algorithms for Vision-Based Navigation. Traditional validation methods such as synthetic rendering or robotic testbed acquisition suffer from difficult setup and slow runtime. Instead, we propose augmenting image datasets in real-time with synthesized views at novel poses. This approach creates continuous trajectories from sparse, pre-existing datasets in open or closed-loop. In addition, we introduce a new distance metric between camera poses, the Boresight Deviation Distance, which is better suited for view synthesis than existing metrics. Using it, a method for increasing the density of image datasets is developed.
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。