English

KRONC: Keypoint-based Robust Camera Optimization for 3D Car Reconstruction

Computer Vision and Pattern Recognition 2024-09-10 v1

Abstract

The three-dimensional representation of objects or scenes starting from a set of images has been a widely discussed topic for years and has gained additional attention after the diffusion of NeRF-based approaches. However, an underestimated prerequisite is the knowledge of camera poses or, more specifically, the estimation of the extrinsic calibration parameters. Although excellent general-purpose Structure-from-Motion methods are available as a pre-processing step, their computational load is high and they require a lot of frames to guarantee sufficient overlapping among the views. This paper introduces KRONC, a novel approach aimed at inferring view poses by leveraging prior knowledge about the object to reconstruct and its representation through semantic keypoints. With a focus on vehicle scenes, KRONC is able to estimate the position of the views as a solution to a light optimization problem targeting the convergence of keypoints' back-projections to a singular point. To validate the method, a specific dataset of real-world car scenes has been collected. Experiments confirm KRONC's ability to generate excellent estimates of camera poses starting from very coarse initialization. Results are comparable with Structure-from-Motion methods with huge savings in computation. Code and data will be made publicly available.

Keywords

Cite

@article{arxiv.2409.05407,
  title  = {KRONC: Keypoint-based Robust Camera Optimization for 3D Car Reconstruction},
  author = {Davide Di Nucci and Alessandro Simoni and Matteo Tomei and Luca Ciuffreda and Roberto Vezzani and Rita Cucchiara},
  journal= {arXiv preprint arXiv:2409.05407},
  year   = {2024}
}

Comments

Accepted at ECCVW

R2 v1 2026-06-28T18:38:12.470Z