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. Our code is released at \url{https://github.com/zhenpeiyang/FvOR/}
@article{arxiv.2205.07763,
title = {FvOR: Robust Joint Shape and Pose Optimization for Few-view Object Reconstruction},
author = {Zhenpei Yang and Zhile Ren and Miguel Angel Bautista and Zaiwei Zhang and Qi Shan and Qixing Huang},
journal= {arXiv preprint arXiv:2205.07763},
year = {2022}
}