arXiv Computer Vision

Bootstrapping a 4D LiDAR Annotation Tool from Video Foundation Models

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 Computer Vision

Oct 2

Lang3DSeg: Annotation-Free Open-Vocabulary 3D Segmentation with Point Transformers

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

llms agents computer-vision multimodal benchmarks

arXiv Computer Vision

Sep 25

SplatLabel: Pseudo-Labelling through 4D Gaussian Splatting

SplatLabel is an automated pipeline that uses a 4D Gaussian representation to generate LiDAR segmentation and semantic occupancy grids with predictive confidence. It models dynamic scenes through an explicit temporal manifold, tracking moving actors without requiring pre‑annotated 3D bounding boxes. By integrating 360‑degree LiDAR depth maps and distilling soft probabilities from 2D models, it resolves semantic ambiguities over time and space, and evaluates pseudo‑labels via a selective classification framework that balances precision and recall.

By Nitya Nanvani, Andras Palffy, Holger Caesar

llms computer-vision benchmarks

arXiv AI

Jun 24

HilDA: Hierarchical Distillation with Diffusion for Advancing Self-Supervised LiDAR Pre-training

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).

By Maciej Wozniak, Jesper Ericsson, Hariprasath Govindarajan, Truls Nyberg, Thomas Gustafsson, Patric Jensfelt, Olov Andersson

agents diffusion computer-vision robotics efficiency multimodal benchmarks safety

arXiv AI

Jun 19

HilDA: Hierarchical Distillation with Diffusion for Advancing Self-Supervised LiDAR Pre-trainin

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).

By Maciej Wozniak, Jesper Ericsson, Hariprasath Govindarajan, Truls Nyberg, Thomas Gustafsson, Patric Jensfelt, Olov Andersson

agents diffusion computer-vision robotics efficiency multimodal benchmarks safety

arXiv Computer Vision

Sep 10

Geometry Without Coordinates: LiDAR Diffusion as a 3D Feature Bridge

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...

By Samed Do\u{g}an, Nico Leuze, Alfred Sch\"ottl

diffusion computer-vision

arXiv Computer Vision

Aug 24

Vision Foundation Model Driven Foreground-Aware Pseudo-LiDAR Generation for Monocular 3D Object Detection

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

computer-vision benchmarks

arXiv Computer Vision

Aug 24

Stream3Dv2: Geometric-Semantic Fusion Enhanced Streaming Zero-Shot 3D Scene Understanding

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...

By Jie Xu, Na Zhao

llms agents computer-vision robotics

arXiv AI

Sep 30

Training-Free Global Geometric Association for 4D LiDAR Panoptic Segmentation

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

computer-vision benchmarks

arXiv Computer Vision

Sep 15

Unsupervised Point Cloud Registration via Training-Time Semantic Guidance

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...

By Kezheng Xiong, Shiyun Xu, Sheng Ao, Siqi Shen, Cheng Wang, Chenglu Wen

computer-vision efficiency benchmarks

arXiv Computer Vision

Sep 22

Towards robust multimodal 3D object detection via visual foundation models

arXiv:2609.23541v1 Announce Type: new Abstract: Multimodal 3D object detection is fundamental to robust perception in autonomous driving because it integrates complementary information from LiDAR and...

By Ziying Song, Lin Liu, Hongyu Pan, Shaoqing Xu, Lei Yang, Mingzhe Guo, Caiyan Jia

agents computer-vision robotics multimodal benchmarks

arXiv AI

Jul 2

Cross4D-JEPA: Dense Cross-modal Correspondence Distillation for 4D Point Cloud Representation Learning

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.

By Trung Thanh Nguyen, Hai Nguyen-Truong, Tu Vo, Hoang M. Truong, Tuan-Anh Vu

rag diffusion robotics fine-tuning efficiency multimodal benchmarks

arXiv Computer Vision

Sep 16

SSC-Priors: Exploring Semantic and Visibility Priors to Boost Lidar Semantic Scene Completion

arXiv:2609.17413v1 Announce Type: new Abstract: This paper investigates easy strategies to boost the performance of existing networks for lidar semantic scene completion (SSC) without requiring compl...

By Tetiana Martyniuk, Jonathan Seele, Alexandre Boulch, Gilles Puy, Renaud Marlet, Raoul de Charette

computer-vision benchmarks

Related stories