CalibRefine: Deep Learning-Based Online Automatic Targetless LiDAR-Camera Calibration with Iterative and Attention-Driven Post-Refinement
L. Cheng, L. Guo, T. Zhang, T. Bang, A. Harris, M. Hajij, M. Sartipi, S. Cao
IEEE Transactions on Instrumentation and Measurement, 2026 , Vol. 75 , pp. 1-18
Abstract
CalibRefine is a fully automatic, targetless, and online calibration framework that directly processes raw LiDAR point clouds and camera images. The approach features a Common Feature Discriminator, coarse homography-based calibration, iterative refinement, and attention-based refinement using Vision Transformer and cross-attention mechanisms to address non-planar distortions. Achieves high-precision calibration with minimal human input.
Citation
L. Cheng, L. Guo, T. Zhang, T. Bang, A. Harris, M. Hajij, M. Sartipi, S. Cao. "CalibRefine: Deep Learning-Based Online Automatic Targetless LiDAR-Camera Calibration with Iterative and Attention-Driven Post-Refinement." IEEE Transactions on Instrumentation and Measurement 75: 1-18, 2026. DOI: 10.1109/TIM.2025.3647989
Publication Snapshot
- Authors
- L. Cheng, L. Guo, T. Zhang, T. Bang, A. Harris, M. Hajij, M. Sartipi, S. Cao
- Venue
- IEEE Transactions on Instrumentation and Measurement
- Published
- 2026
- Pages
- 1-18