Efficient texture mapping via a non-iterative global texture alignment

TL;DR

This paper introduces a fast, non-iterative global texture alignment method for 3D scenes that improves texture mapping accuracy and efficiency by automatically selecting keyframes, geometrically matching fragments, and solving a linear system.

Contribution

It presents a novel non-iterative global optimization framework for seamless texture reconstruction, reducing computational complexity and enhancing alignment accuracy.

Findings

Low computational complexity demonstrated in experiments

Outperforms existing alignment methods in accuracy

Effective reduction of visual seams through color correction

Abstract

Texture reconstruction techniques generally suffer from the errors in keyframe poses. We present a non-iterative method for seamless texture reconstruction of a given 3D scene. Our method finds the best texture alignment in a single shot using a global optimisation framework. First, we automatically select the best keyframe to texture each face of the mesh. This leads to a decomposition of the mesh into small groups of connected faces associated to a same keyframe. We call such groups fragments. Then, we propose a geometry-aware matching technique between the 3D keypoints extracted around the fragment borders, where the matching zone is controlled by the margin size. These constraints lead to a least squares (LS) model for finding the optimal alignment. Finally, visual seams are further reduced by applying a fast colour correction. In contrast to pixel-wise methods, we find the optimal alignment by solving a sparse system of linear equations, which is very fast and non-iterative. Experimental results demonstrate low computational complexity and outperformance compared to other alignment methods.