Robust Multi-view Camera Calibration from Dense Matches

TL;DR

This paper presents a robust multi-view camera calibration method that improves accuracy in pose estimation, especially for cameras with radial distortion, by optimizing correspondence subsampling and view selection in SfM pipelines.

Contribution

The paper introduces novel strategies for subsampling dense matches and selecting views, enhancing calibration accuracy in multi-camera setups with radial distortion.

Findings

Significant accuracy improvement for cameras with radial distortion (79.9% vs. 40.4%)

Effective correspondence subsampling in global SfM pipelines

Generalizes across diverse camera configurations

Abstract

Estimating camera intrinsics and extrinsics is a fundamental problem in computer vision, and while advances in structure-from-motion (SfM) have improved accuracy and robustness, open challenges remain. In this paper, we introduce a robust method for pose estimation and calibration. We consider a set of rigid cameras, each observing the scene from a different perspective, which is a typical camera setup in animal behavior studies and forensic analysis of surveillance footage. Specifically, we analyse the individual components in a structure-from-motion (SfM) pipeline, and identify design choices that improve accuracy. Our main contributions are: (1) we investigate how to best subsample the predicted correspondences from a dense matcher to leverage them in the estimation process. (2) We investigate selection criteria for how to add the views incrementally. In a rigorous quantitative evaluation, we show the effectiveness of our changes, especially for cameras with strong radial distortion (79.9% ours vs. 40.4 vanilla VGGT). Finally, we demonstrate our correspondence subsampling in a global SfM setting where we initialize the poses using VGGT. The proposed pipeline generalizes across a wide range of camera setups, and could thus become a useful tool for animal behavior and forensic analysis.