SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

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

Read original source ↗ Open in workspace

recordType

paper

region

Global