The Flow has not summarised this story yet — read it at arXiv Computer Vision.
DXPR is a depth‑based cross‑modal place recognition framework that matches monocular camera queries to a LiDAR map using a single vision foundation model backbone. By converting both modalities into a unified depth image representation, DXPR learns modality‑invariant global descriptors without modality‑specific encoders. A geometry‑aware overlap miner refines pairwise metric learning by computing pixel‑level overlap scores, and extensive tests on KITTI and Boreas show strong performance across seasons, weather, and day/night conditions, outperforming prior CMPR baselines.
Learning-based global point cloud registration has achieved remarkable progress, yet its reliance on geometric representations makes existing methods sensitive to variations in point density, scan pattern, viewpoint, and sensor characteristics. We propose CVSD-Reg, a robust global LiDAR registration framework that distills visual semantic priors from a vision foundation model into LiDAR representations.
The paper introduces a method that combines large language models (LLMs) with LiDAR geometry to answer complex spatial questions by grounding targets directly in LiDAR point clouds. It presents the SpatialLiDAR-QA dataset for relational grounding tasks and the SpatialLiDAR-LM model, which aligns LiDAR features with an LLM to retrieve and refine target coordinates. Experiments show significant gains over existing LiDAR–language models and multi‑camera vision‑language models in precise coordinate prediction.
arXiv:2608. 19536v1 Announce Type: cross Abstract: Learning-based global point cloud registration has achieved remarkable progress, yet its reliance on geometric representations makes existing methods sensitive to variations in point density, scan pattern, viewpoint, and sensor characteristics.
UpDown‑SC is a training‑free polar descriptor for indoor LiDAR place recognition that first canonicalizes gravity and then represents two complementary surfaces: the upper envelope of lower/middle structures and the lower envelope of overhead structures. By estimating a physical split from a cell‑balanced map height distribution and using a mask‑aware, non‑uniform two‑channel distance, it retains discriminative lower‑level evidence while limiting sensitivity to cross‑session variation. Experiments on repeated indoor sessions, mounting‑height changes, mixed outdoor‑to‑indoor trajectories, and an outdoor transfer sequence demonstrate more reliable first‑choice retrieval and significant gains over conventional Scan Context, while maintaining a lightweight CPU front end and supporting metric prior‑map localization.
Scene coordinate regression (SCR) achieves strong performance in outdoor LiDAR localization, but it usually requires scene-specific training that can take days, limiting practical deployment. Recent w...