Lang3DSeg introduces a point‑transformer backbone for open‑vocabulary, annotation‑free 3D LiDAR segmentation, trained from scratch without geometric pre‑training. It tackles noise from 2D‑to‑3D label projections by applying a class‑priority rule and truncating projected instances at depth gaps, thereby correcting depth‑ambiguity errors. The method achieves state‑of‑the‑art results on nuScenes (52.8 % mIoU) and SemanticKITTI (41.4 % mIoU) while operating in real‑time on a single LiDAR sweep.
By Cigdem Kokenoz, Amir Salarpour, Alkim Domeke, Christopher Salas, Pedram MohajerAnsari, Long Cheng, Mert D. Pes\'e, Bing Li
arXiv:2605.31177v2 Announce Type: replace
Abstract: Plain Transformers have become the de-facto architecture for processing text, audio, image, and video, offering a unified backbone for multimodal l...
By Gilles Puy, Nermin Samet, Alexandre Boulch, Spyros Gidaris, Tuan-Hung VU, Renaud Marlet
arXiv:2603.06168v4 Announce Type: replace
Abstract: Semantic segmentation across visual modalities such as 3D point clouds and panoramic images remains a challenging task, primarily due to the scarci...
By Sandeep Inuganti, Hideaki Kanayama, Kanta Shimizu, Mahdi Chamseddine, Soichiro Yokota, Didier Stricker, Jason Rambach
AutoExpert proposes a new benchmark for automating 3D LiDAR annotation using expert‑crafted guidelines, redefining evaluation protocols and re‑annotating nuScenes and PandaSet datasets. The pipeline combines 2D detection and segmentation in RGB images, lifts these detections into 3D with known sensor poses, and generates 3D cuboids, improving 3D detection mAP from 12.1 to 25.4 on the AutoExpert‑nuScenes benchmark.
By Yechi Ma, Wei Hua, Shu Kong
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.
By Jihun Kim, Hyun-Kurl Jang, Hyemin Yang, Jinnyeong Yang, Hyeokjun Kweon, Kuk-Jin Yoon
arXiv:2404.09431v3 Announce Type: replace
Abstract: Pseudo-LiDAR has become a promising paradigm for monocular 3D object detection by transforming monocular images into point cloud representations th...
By Bonan Ding, Jin Xie, Jing Nie, Jiale Cao, Yanwei Pang