FvOR: Robust Joint Shape and Pose Optimization for Few-View Object Reconstruction
Abstract
Reconstructing an accurate 3D object model from a few image observations remains a challenging problem in computer vision. State-of-the-art approaches typically assume accurate camera poses as input, which could be difficult to obtain in realistic settings. In this paper, we present FvOR, a learning-based object reconstruction method that predicts accurate 3D models given a few images with noisy input poses. The core of our approach is a fast and robust multi-view reconstruction algorithm to jointly refine 3D geometry and camera pose estimation using learnable neural network modules. We provide a thorough benchmark of state-of-the-art approaches for this problem on ShapeNet. Our approach achieves best-in-class results. It is also two orders of magnitude faster than the recent optimization-based approach IDR.
Cite
Text
Yang et al. "FvOR: Robust Joint Shape and Pose Optimization for Few-View Object Reconstruction." Conference on Computer Vision and Pattern Recognition, 2022. doi:10.1109/CVPR52688.2022.00253Markdown
[Yang et al. "FvOR: Robust Joint Shape and Pose Optimization for Few-View Object Reconstruction." Conference on Computer Vision and Pattern Recognition, 2022.](https://mlanthology.org/cvpr/2022/yang2022cvpr-fvor/) doi:10.1109/CVPR52688.2022.00253BibTeX
@inproceedings{yang2022cvpr-fvor,
title = {{FvOR: Robust Joint Shape and Pose Optimization for Few-View Object Reconstruction}},
author = {Yang, Zhenpei and Ren, Zhile and Bautista, Miguel Angel and Zhang, Zaiwei and Shan, Qi and Huang, Qixing},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2022},
pages = {2497-2507},
doi = {10.1109/CVPR52688.2022.00253},
url = {https://mlanthology.org/cvpr/2022/yang2022cvpr-fvor/}
}