We study the problem of aligning a video that captures a local portion of an
environment to the 2D LiDAR scan of the entire environment. We introduce a
method (VioLA) that starts with building a semantic map of the local scene from
the image sequence, then extracts points at a fixed height for registering to
the LiDAR map. Due to reconstruction errors or partial coverage of the camera
scan, the reconstructed semantic map may not contain sufficient information for
registration. To address this problem, VioLA makes use of a pre-trained
text-to-image inpainting model paired with a depth completion model for filling
in the missing scene content in a geometrically consistent fashion to support
pose registration. We evaluate VioLA on two real-world RGB-D benchmarks, as
well as a self-captured dataset of a large office scene. Notably, our proposed
scene completion module improves the pose registration performance by up to
20%.

研究通过建立语义地图和利用图像序列与 LiDAR 扫描进行地点对齐的问题。提出了一种名为 VioLA 的方法，在固定高度提取用于注册到 LiDAR 地图的点。使用预训练的文本到图像修复模型和深度补全模型填补缺失的场景内容以支持姿态注册。在两个真实的 RGB-D 基准数据集以及一个大型办公场景的自录数据集上对 VioLA 进行评估。尤其值得注意的是，我们提出的场景补全模块将姿态注册性能提高了 20%。