# PRaDA: Projective Radial Distortion Averaging

arXiv: https://arxiv.org/abs/2504.16499 · HTML: https://mlsanity.com/paper/2504.16499/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 63 references that are in the map.
- First posted on arXiv 23 Apr 2025.

## Builds on (most cited first, 22 of 22)

- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2108.10869/) (2021)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [Global Structure-from-Motion Revisited](https://mlsanity.com/paper/2407.20219/) (2024)
- [Self-Calibrating Neural Radiance Fields](https://mlsanity.com/paper/2108.13826/) (2021)
- [Back to the Feature: Learning Robust Camera Localization from Pixels to Pose](https://mlsanity.com/paper/2103.09213/) (2021)
- [MAGSAC++, a fast, reliable and accurate robust estimator](https://mlsanity.com/paper/1912.05909/) (2019)
- [WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving](https://mlsanity.com/paper/1905.01489/) (2019)
- [MAGSAC: marginalizing sample consensus](https://mlsanity.com/paper/1803.07469/) (2018)
- [Perspective Fields for Single Image Camera Calibration](https://mlsanity.com/paper/2212.03239/) (2022)
- [A Perceptual Measure for Deep Single Image Camera Calibration](https://mlsanity.com/paper/1712.01259/) (2017)
- [Algebraic Characterization of Essential Matrices and Their Averaging in Multiview Settings](https://mlsanity.com/paper/1904.02663/) (2019)
- [GPSfM: Global Projective SFM Using Algebraic Constraints on Multi-View Fundamental Matrices](https://mlsanity.com/paper/1812.00426/) (2018)
- [Minimal Solvers for Single-View Lens-Distorted Camera Auto-Calibration](https://mlsanity.com/paper/2011.08988/) (2020)
- [Power Variable Projection for Initialization-Free Large-Scale Bundle Adjustment](https://mlsanity.com/paper/2405.05079/) (2024)
- [Neural Lens Modeling](https://mlsanity.com/paper/2304.04848/) (2023)
- [Revisiting Sampson Approximations for Geometric Estimation Problems](https://mlsanity.com/paper/2401.07114/) (2024)
- [Cauchy Loss Function: Robustness Under Gaussian and Cauchy Noise](https://mlsanity.com/paper/2302.07238/) (2023)

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

- [RayTun3R: Online Camera Adaptation in 3D Foundation Models](https://mlsanity.com/paper/2607.02711/) (2026)

## Abstract (arXiv)

We tackle the problem of automatic calibration of radially distorted cameras in challenging conditions. Accurately determining distortion parameters typically requires either 1) solving the full Structure from Motion (SfM) problem involving camera poses, 3D points, and the distortion parameters, which is only possible if many images with sufficient overlap are provided, or 2) relying heavily on learning-based methods that are comparatively less accurate. In this work, we demonstrate that distortion calibration can be decoupled from 3D reconstruction, maintaining the accuracy of SfM-based methods while avoiding many of the associated complexities. This is achieved by working in Projective Space, where the geometry is unique up to a homography, which encapsulates all camera parameters except for distortion. Our proposed method, Projective Radial Distortion Averaging, averages multiple distortion estimates in a fully projective framework without creating 3d points and full bundle adjustment. By relying on pairwise projective relations, our methods support any feature-matching approaches without constructing point tracks across multiple images.