Efficient texture mapping via a non-iterative global texture alignment
This addresses texture mapping errors in 3D reconstruction for applications like computer graphics and vision, but it is incremental as it builds on existing texture alignment techniques.
The paper tackles the problem of texture reconstruction errors due to inaccurate keyframe poses by introducing a non-iterative global optimization method for seamless texture mapping, achieving low computational complexity and outperforming other alignment methods.
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.