KRONC: Keypoint-based Robust Camera Optimization for 3D Car Reconstruction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929492212056064 |
|---|---|
| author | Di Nucci, Davide Simoni, Alessandro Tomei, Matteo Ciuffreda, Luca Vezzani, Roberto Cucchiara, Rita |
| author_facet | Di Nucci, Davide Simoni, Alessandro Tomei, Matteo Ciuffreda, Luca Vezzani, Roberto Cucchiara, Rita |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_05407 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | KRONC: Keypoint-based Robust Camera Optimization for 3D Car Reconstruction Di Nucci, Davide Simoni, Alessandro Tomei, Matteo Ciuffreda, Luca Vezzani, Roberto Cucchiara, Rita Computer Vision and Pattern Recognition 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. |
| title | KRONC: Keypoint-based Robust Camera Optimization for 3D Car Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.05407 |