DRS-VPT: Directly Relocalizing in a Scan with Vision Point Transformers

2026-09-11

AI Summary

该研究提出DRS-VPT模型，通过视觉点变换器直接解决图像与3D扫描配准问题，实现高精度的相机-LiDAR校准及室内重定位。

Abstract

We present DRS-VPT, a feed-forward transformer architecture for foundational image-to-scan registration. Given query images and a reference 3D point cloud, the model predicts the scan pose and point map alongside the poses and point maps of each camera, all expressed in the first camera's frame. It additionally predicts a coarse-to- fine pyramid of per-point and per-pixel features for direct reprojective alignment of the scan to the first image. This formulation unifies downstream tasks such as camera-LiDAR calibration in autonomous driving and indoor camera-to-map relocalization. A single DRS-VPT model achieves state-of-the-art performance for image-to-LiDAR registration in autonomous driving, competitive indoor relocalization without training map-specific weights, and strong zero-shot transfer to unseen environments. We also show qualitatively that the model learns complex scan-to-image projection properties such as occlusion of back-facing points.

Problem

• image-to-scan registration
• camera-LiDAR calibration
• indoor relocalization

Innovation

• Direct Relocalization
• Vision Point Transformers
• Image-to-Scan Registration
• Coarse-to-Fine Pyramid