Scalable Dense Monocular Surface Reconstruction

TL;DR

This paper introduces SMSR, a scalable monocular surface reconstruction method that effectively handles various data types and motions, achieving state-of-the-art accuracy with efficient algorithms.

Contribution

The paper presents a novel, scalable monocular surface reconstruction approach that integrates trajectory constraints and converges efficiently, outperforming existing methods.

Findings

Achieves state-of-the-art accuracy across diverse datasets.

Handles sparse and dense data, as well as different motions.

Converges in linear time for large matrices.

Abstract

This paper reports on a novel template-free monocular non-rigid surface reconstruction approach. Existing techniques using motion and deformation cues rely on multiple prior assumptions, are often computationally expensive and do not perform equally well across the variety of data sets. In contrast, the proposed Scalable Monocular Surface Reconstruction (SMSR) combines strengths of several algorithms, i.e., it is scalable with the number of points, can handle sparse and dense settings as well as different types of motions and deformations. We estimate camera pose by singular value thresholding and proximal gradient. Our formulation adopts alternating direction method of multipliers which converges in linear time for large point track matrices. In the proposed SMSR, trajectory space constraints are integrated by smoothing of the measurement matrix. In the extensive experiments, SMSR is demonstrated to consistently achieve state-of-the-art accuracy on a wide variety of data sets.