arXiv:2506. 22784v2 Announce Type: replace-cross Abstract: Point-pixel registration between LiDAR point clouds and camera images is a fundamental yet challenging task in autonomous driving and robotic perception.
By Yu Han, Zhiwei Huang, Yanting Zhang, Fangjun Ding, Shen Cai, Xiaoyu Tang, Yanchao Dong, Rui Fan
Glass Surface Detection Grounded in 3D Visual Geometry proposes a new approach that grounds glass surface detection in 3D visual geometry rather than relying solely on 2D appearance cues. The method uses a visual geometry grounded transformer (VGGT) to distill 3D priors and creates glass-aware 3D representations, then applies a multi-task learning framework with a Frequency Self-Attention Module (FSAM) and a Geometry Grounding Block (GeGB) to localize and segment glass surfaces. Experiments show state‑of‑the‑art performance on seven benchmarks, good generalization to video and multi‑modal data, and significant improvements in reconstruction of glass scenes.
By Yiwei Lu, Ke Xu, Tao Yan, Xiaojun Chang, Radu Timofte, Rynson W. H. Lau
arXiv:2512.18991v3 Announce Type: replace-cross
Abstract: Dominant paradigms for 4D LiDAR panoptic segmentation are usually required to train deep neural networks with large superimposed point clouds...
By Gyeongrok Oh, Youngdong Jang, Jonghyun Choi, Suk-Ju Kang, Guang Lin, Sangpil Kim
The paper presents a close‑range photogrammetry workflow using Structure‑from‑Motion and Multi‑View Stereo to generate high‑resolution 3D point clouds of rubberised concrete. By capturing images with a Canon DSLR and an iPhone 16, the authors achieved sub‑millimetre reconstruction accuracy, outperforming traditional LiDAR for fine‑scale defect analysis. An RGB‑guided crack extraction method and deformation analysis further demonstrate the method’s utility for detailed surface monitoring and material performance evaluation.
By Jiacheng Liu, Mohammed Alnahhal, Ailar Hajimohammadi, Sara Gonizzi Barsanti, Jinling Wang, Mohsen Kalantari
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:2606. 28607v1 Announce Type: cross Abstract: This work tackles the challenge of enhancing low-resolution LiDAR sensors for SLAM applications through a novel Deep Unrolling-based Super-Resolution (SR) model.
By Christos Anagnostopoulos, Alexandros Gkillas, Nikos Piperigkos, Aris S. Lalos