Research map / Point clouds / Point cloud classification
Cross-Modal Prior-Guided Training with Visual Foundation Models for Unsupervised LiDAR Point Cloud Registration
KeZheng Xiong, Shiyun Xu, Sheng Ao, Mingming Wang, Siqi Shen, Chenglu Wen, Cheng Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes using visual foundation models as cross-modal priors to train an unsupervised LiDAR point cloud registration model for outdoor scenes.
Problem
Unsupervised LiDAR point cloud registration in outdoor scenes, where data is sparse and irregular, and it is unclear whether visual foundation model benefits seen in indoor RGB-D registration transfer.
Approach
Uses visual foundation models as cross-modal priors to guide label-free training of LiDAR registration, extending the VFM-based indoor RGB-D registration idea to outdoor LiDAR data.
Closest papers by meaning
- FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators (ICLR 2024 · similarity 0.88)
- GeoNLF: Geometry guided Pose-Free Neural LiDAR Fields (NeurIPS 2024 · similarity 0.87)
- Fine-grained Image-to-LiDAR Contrastive Distillation with Visual Foundation Models (NeurIPS 2024 · similarity 0.87)
- TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception (NeurIPS 2025 · similarity 0.87)
- Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration (NeurIPS 2024 · similarity 0.87)
- MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection (ICLR 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
