# Degeneracy in Self-Calibration Revisited and a Deep Learning Solution for Uncalibrated SLAM

arXiv: https://arxiv.org/abs/1907.13185 · HTML: https://mlsanity.com/paper/1907.13185/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2019.

## Built on by (most cited first, 10 of 10)

- [Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild](https://mlsanity.com/paper/2207.10660/) (2022)
- [MUSt3R: Multi-view Network for Stereo 3D Reconstruction](https://mlsanity.com/paper/2503.01661/) (2025)
- [GeoCalib: Learning Single-image Calibration with Geometric Optimization](https://mlsanity.com/paper/2409.06704/) (2024)
- [Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering](https://mlsanity.com/paper/2105.13353/) (2021)
- [Deep Learning for Camera Calibration and Beyond: A Survey](https://mlsanity.com/paper/2303.10559/) (2023)
- [Transformers in Self-Supervised Monocular Depth Estimation with Unknown Camera Intrinsics](https://mlsanity.com/paper/2202.03131/) (2022)
- [Timestamp-Supervised Action Segmentation with Graph Convolutional Networks](https://mlsanity.com/paper/2206.15031/) (2022)
- [Fusing the Old with the New: Learning Relative Camera Pose with Geometry-Guided Uncertainty](https://mlsanity.com/paper/2104.08278/) (2021)
- [Rolling Shutter Camera Self-Calibration](https://mlsanity.com/paper/2608.01509/) (2026)
- [VGGT-GS SLAM: Uncalibrated Monocular Gaussian Splatting SLAM with Feed-Forward Priors](https://mlsanity.com/paper/2609.19628/) (2026)

## Abstract (arXiv)

Self-calibration of camera intrinsics and radial distortion has a long history of research in the computer vision community. However, it remains rare to see real applications of such techniques to modern Simultaneous Localization And Mapping (SLAM) systems, especially in driving scenarios. In this paper, we revisit the geometric approach to this problem, and provide a theoretical proof that explicitly shows the ambiguity between radial distortion and scene depth when two-view geometry is used to self-calibrate the radial distortion. In view of such geometric degeneracy, we propose a learning approach that trains a convolutional neural network (CNN) on a large amount of synthetic data. We demonstrate the utility of our proposed method by applying it as a checkerboard-free calibration tool for SLAM, achieving comparable or superior performance to previous learning and hand-crafted methods.