arXiv:2608.29003v1 Announce Type: cross Abstract: In dynamic and unstructured environments, conventional SLAM systems generally suffer from significant accuracy degeneration due to their static assum...
The paper introduces LiDAR‑SAM2, a framework that converts the 2D video foundation model SAM2 into a scalable source of supervision for 4D LiDAR data. By projecting SAM2 video masks into multi‑view LiDAR space and aggregating them temporally, the method automatically generates temporally coherent LiDAR labels without human annotation. Experiments on SemanticKITTI show that these automatically produced semantic and panoptic labels achieve quality close to full human annotation, enabling models trained on them to approach the performance of fully supervised systems.
arXiv:2609.10322v1 Announce Type: new Abstract: Transferring the rich priors of large 2D foundation models to sparse 3D LiDAR remains challenging, as training native 3D foundation models at comparabl...
arXiv:2608.21136v1 Announce Type: new Abstract: Recently, open-vocabulary zero-shot 3D scene understanding using vision foundation models has emerged as a promising alternative to data-intensive supe...
arXiv:2609.27850v1 Announce Type: new Abstract: 3D Gaussian Splatting provides an efficient representation for 3D reconstruction, and recent extensions attach semantic attributes to Gaussians for ope...
arXiv:2609.09012v2 Announce Type: replace Abstract: Spherical observations provide global visual context for 3D scene understanding. However, visual information is encoded in an angular domain, where...
arXiv:2609.15228v1 Announce Type: new Abstract: Unsupervised registration of large-scale LiDAR point clouds remains challenging due to the geometric ambiguity inherent in outdoor scenes, which degrad...
arXiv:2605.25059v4 Announce Type: replace Abstract: Crucial for autonomous exploration, online 3D occupancy prediction and mapping incrementally construct dense spatial representations on the fly. Em...
arXiv:2609.24825v1 Announce Type: new Abstract: LiDAR point clouds acquired in underground environments exhibit severe geometric incompleteness due to occlusions and limited sensor viewpoints, making...
arXiv:2606. 20189v3 Announce Type: replace-cross Abstract: Leveraging Vision Foundation Models (VFMs) for camera-to-LiDAR knowledge distillation offers a promising solution to the scarcity of annotated data needed to represent the immense geometric and kinematic diversity of real-world autonomous driving (AD).
arXiv:2606. 20189v1 Announce Type: cross Abstract: Leveraging Vision Foundation Models (VFMs) for camera-to-LiDAR knowledge distillation offers a promising solution to the scarcity of annotated data needed to represent the immense geometric and kinematic diversity of real-world autonomous driving (AD).
DIAL-GS introduces a dynamic instance-aware reconstruction technique for label-free street scenes using 4D Gaussian Splatting. It identifies dynamic instances by detecting appearance-position inconsistencies between warped renderings and actual observations, then employs instance-aware 4D Gaussians to create a unified volumetric representation that adapts to dynamics. A reciprocal mechanism further strengthens identity and dynamics, leading to improved reconstruction quality and instance-level editing compared to existing self-supervised baselines.