Local Readjustment for High-Resolution 3D Reconstruction

Siyu Zhu, Tian Fang, Jianxiong Xiao, Long Quan; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014, pp. 3938-3945


Global bundle adjustment usually converges to a non-zero residual and produces sub-optimal camera poses for local areas, which leads to loss of details for high- resolution reconstruction. Instead of trying harder to optimize everything globally, we argue that we should live with the non-zero residual and adapt the camera poses to local areas. To this end, we propose a segment-based approach to readjust the camera poses locally and improve the reconstruction for fine geometry details. The key idea is to partition the globally optimized structure from motion points into well-conditioned segments for re-optimization, reconstruct their geometry individually, and fuse everything back into a consistent global model. This significantly reduces severe propagated errors and estimation biases caused by the initial global adjustment. The results on several datasets demonstrate that this approach can significantly improve the reconstruction accuracy, while maintaining the consistency of the 3D structure between segments.

Related Material

author = {Zhu, Siyu and Fang, Tian and Xiao, Jianxiong and Quan, Long},
title = {Local Readjustment for High-Resolution 3D Reconstruction},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2014}