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).
arXiv:2607. 10762v1 Announce Type: cross Abstract: Cross-modal distillation from Vision Foundation Models (VFMs) to LiDAR backbones has recently emerged as a self-supervised pretraining strategy that reduces reliance on dense point-wise annotation for 3D scene understanding.
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.
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.
arXiv:2608. 19973v1 Announce Type: cross Abstract: Recently, open-vocabulary 3D object detection (3D-OVD) has gained increasing attention for its ability to detect unseen objects in 3D scenes.
arXiv:2606. 02979v1 Announce Type: cross Abstract: We present a novel compact deep multi-task learning model to handle various autonomous driving perception tasks in one forward pass.
arXiv:2607. 00514v1 Announce Type: cross Abstract: Automatic understanding of dynamic 4D point clouds, the 3D-point sequences captured over time by depth sensors and LiDAR, is central to robotics and embodied perception.
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...
arXiv:2605.07326v2 Announce Type: replace Abstract: World models, which simulate environmental dynamics and generate sensor observations, are gaining increasing attention in autonomous driving. Howev...
Large 3D foundation models such as MASt3R achieve state-of-the-art stereo reconstruction but are computationally demanding for deployment under strict hardware constraints -- a critical limitation in domains such as planetary exploration, where onboard computing is severely restricted. We study how far such models can be compressed through knowledge distillation, using lunar stereo reconstruction as a challenging and practically relevant case study.
Vision Transformers underperform convolutional networks when training data is scarce, and distilling convolutional inductive biases from a CNN teacher is an effective remedy that leaves the deployed model unchanged. General-purpose feature distillation, however, transfers little in this setting.