Dense Non-rigid Structure-from-Motion Made Easy - A Spatial-Temporal Smoothness based Solution

TL;DR

This paper introduces a simple, robust, and effective spatial-temporal smoothness based approach for dense non-rigid structure-from-motion, improving reconstruction accuracy and robustness to noise and outliers.

Contribution

It extends temporal smoothness to dense cases, incorporates spatial smoothness via the Laplacian, and robustifies the data term with L1 norm, making dense NRSfM easier and more accurate.

Findings

Outperforms state-of-the-art dense NRSfM methods

Robust to noise and outliers in measurements

Simple implementation involving least squares problems

Abstract

This paper proposes a simple spatial-temporal smoothness based method for solving dense non-rigid structure-from-motion (NRSfM). First, we revisit the temporal smoothness and demonstrate that it can be extended to dense case directly. Second, we propose to exploit the spatial smoothness by resorting to the Laplacian of the 3D non-rigid shape. Third, to handle real world noise and outliers in measurements, we robustify the data term by using the $L_1$ norm. In this way, our method could robustly exploit both spatial and temporal smoothness effectively and make dense non-rigid reconstruction easy. Our method is very easy to implement, which involves solving a series of least squares problems. Experimental results on both synthetic and real image dense NRSfM tasks show that the proposed method outperforms state-of-the-art dense non-rigid reconstruction methods.