Structure From Recurrent Motion: From Rigidity to Recurrency

Xiu Li, Hongdong Li, Hanbyul Joo, Yebin Liu, Yaser Sheikh; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 3032-3040


This paper proposes a new method for Non-rigidstructure-from-motion (NRSfM). Departing significantlyfrom the traditional idea of using linear low-order shapemodel for NRSfM, our method exploits the property of shaperecurrence (i.e. many dynamic shapes tend to repeat them-selves in time). We show that recurrency is in fact agen-eralized rigidity. Based on this, we show how to reduceNRSfM problems to rigid ones, provided that the recurrencecondition is satisfied. Given such a reduction, standardrigid-SFM techniques can be applied directly (without anychange) to reconstruct the non-rigid dynamic shape. To im-plement this idea as a practical approach, this paper de-velops efficient and reliable algorithm for automatic recur-rence detection, as well as new method for camera viewsclustering via rigidity-check. Experiments on both syntheticsequences and real data demonstrate the effectiveness of theproposed method. Since the method provides novel perspec-tive to look at Structure-from-Motion, we hope it will inspireother new researches in the field.

Related Material

[pdf] [arXiv]
author = {Li, Xiu and Li, Hongdong and Joo, Hanbyul and Liu, Yebin and Sheikh, Yaser},
title = {Structure From Recurrent Motion: From Rigidity to Recurrency},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}