TextureFusion: High-Quality Texture Acquisition for Real-Time RGB-D Scanning

Joo Ho Lee

Abstract:

Real-time RGB-D scanning technique has become
widely used to progressively scan objects with a hand-held
sensor. Existing online methods restore color information

per voxel, and thus their quality is often limited by the trade-
off between spatial resolution and time performance. Also,

such methods often suffer from blurred artifacts in the cap-
tured texture. Traditional offline texture mapping methods

with non-rigid warping assume that the reconstructed ge-
ometry and all input views are obtained in advance, and

the optimization takes a long time to compute mesh param-
eterization and warp parameters, which prevents them from

being used in real-time applications. In this work, we pro-
pose a progressive texture-fusion method specially designed

for real-time RGB-D scanning. To this end, we first de-
vise a novel texture-tile voxel grid, where texture tiles are

embedded in the voxel grid of the signed distance func-
tion, allowing for high-resolution texture mapping on the

low-resolution geometry volume. Instead of using expensive

mesh parameterization, we associate vertices of implicit ge-
ometry directly with texture coordinates. Second, we in-
troduce real-time texture warping that applies a spatially-
varying perspective mapping to input images so that texture

warping efficiently mitigates the mismatch between the in-
termediate geometry and the current input view. It allows us

to enhance the quality of texture over time while updating
the geometry in real-time. The results demonstrate that the

quality of our real-time texture mapping is highly compet-
itive to that of exhaustive offline texture warping methods.

Our method is also capable of being integrated into existing
RGB-D scanning frameworks.