fCOP: Focal Length Estimation from Category-level Object Priors

TL;DR

This paper introduces a novel monocular focal length estimation method leveraging category-level object priors, combining depth and shape information to improve accuracy without scene geometry assumptions.

Contribution

It presents a new closed-form focal length estimator that integrates depth and object shape priors from images, outperforming existing methods.

Findings

Outperforms current state-of-the-art on simulated data

Effective on real-world datasets

Provides a practical solution without scene geometry priors

Abstract

In the realm of computer vision, the perception and reconstruction of the 3D world through vision signals heavily rely on camera intrinsic parameters, which have long been a subject of intense research within the community. In practical applications, without a strong scene geometry prior like the Manhattan World assumption or special artificial calibration patterns, monocular focal length estimation becomes a challenging task. In this paper, we propose a method for monocular focal length estimation using category-level object priors. Based on two well-studied existing tasks: monocular depth estimation and category-level object canonical representation learning, our focal solver takes depth priors and object shape priors from images containing objects and estimates the focal length from triplets of correspondences in closed form. Our experiments on simulated and real world data demonstrate that the proposed method outperforms the current state-of-the-art, offering a promising solution to the long-standing monocular focal length estimation problem.