# UniCalib: Targetless LiDAR-Camera Calibration via Probabilistic Flow on Unified Depth Representations

arXiv: https://arxiv.org/abs/2504.01416 · HTML: https://mlsanity.com/paper/2504.01416/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 49 references that are in the map.
- First posted on arXiv 2 Apr 2025.

## Builds on (most cited first, 20 of 20)

- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision](https://mlsanity.com/paper/2410.19115/) (2024)
- [DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2203.08195/) (2022)
- [SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow](https://mlsanity.com/paper/2405.14793/) (2024)
- [ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer](https://mlsanity.com/paper/2208.14201/) (2022)
- [In Defense of Classical Image Processing: Fast Depth Completion on the CPU](https://mlsanity.com/paper/1802.00036/) (2018)
- [PDC-Net+: Enhanced Probabilistic Dense Correspondence Network](https://mlsanity.com/paper/2109.13912/) (2021)
- [LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector](https://mlsanity.com/paper/2108.08258/) (2021)
- [RegNet: Multimodal Sensor Registration Using Deep Neural Networks](https://mlsanity.com/paper/1707.03167/) (2017)
- [CRLF: Automatic Calibration and Refinement based on Line Feature for LiDAR and Camera in Road Scenes](https://mlsanity.com/paper/2103.04558/) (2021)
- [LiDAR-Camera Calibration using 3D-3D Point correspondences](https://mlsanity.com/paper/1705.09785/) (2017)
- [Joint Camera Intrinsic and LiDAR-Camera Extrinsic Calibration](https://mlsanity.com/paper/2202.13708/) (2022)
- [DXQ-Net: Differentiable LiDAR-Camera Extrinsic Calibration Using Quality-aware Flow](https://mlsanity.com/paper/2203.09385/) (2022)
- [CFNet: LiDAR-Camera Registration Using Calibration Flow Network](https://mlsanity.com/paper/2104.11907/) (2021)
- [CalibFormer: A Transformer-based Automatic LiDAR-Camera Calibration Network](https://mlsanity.com/paper/2311.15241/) (2023)
- [RMMDet: Road-Side Multitype and Multigroup Sensor Detection System for Autonomous Driving](https://mlsanity.com/paper/2303.05203/) (2023)
- [RobustCalib: Robust Lidar-Camera Extrinsic Calibration with Consistency Learning](https://mlsanity.com/paper/2312.01085/) (2023)

## Built on by (most cited first, 1 of 1)

- [Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting](https://mlsanity.com/paper/2506.05280/) (2025)

## Abstract (arXiv)

Precise LiDAR-camera calibration is crucial for integrating these two sensors into robotic systems to achieve robust perception. In applications like autonomous driving, online targetless calibration enables a prompt sensor misalignment correction from mechanical vibrations without extra targets. However, existing methods exhibit limitations in effectively extracting consistent features from LiDAR and camera data and fail to prioritize salient regions, compromising cross-modal alignment robustness. To address these issues, we propose DF-Calib, a LiDAR-camera calibration method that reformulates calibration as an intra-modality depth flow estimation problem. DF-Calib estimates a dense depth map from the camera image and completes the sparse LiDAR projected depth map, using a shared feature encoder to extract consistent depth-to-depth features, effectively bridging the 2D-3D cross-modal gap. Additionally, we introduce a reliability map to prioritize valid pixels and propose a perceptually weighted sparse flow loss to enhance depth flow estimation. Experimental results across multiple datasets validate its accuracy and generalization,with DF-Calib achieving a mean translation error of 0.635cm and rotation error of 0.045 degrees on the KITTI dataset.