Seamless Image-Based Texture Atlases using Multi-band Blending
C
´
edric All
`
ene, Jean-Philippe Pons and Renaud Keriven
CERTIS,
´
Ecole des ponts, Paris-Est, France
{allene,pons,keriven}@certis.enpc.fr
Abstract
In this paper, we propose a novel method for creating
a high-quality texture atlas from a 3D model and a set
of calibrated images. Our method focuses on avoiding
visual artifacts such as color discontinuities, ghosting
or blurring, which typically arise from photometric and
geometric inaccuracies. We first compute a partition of
mesh faces which realizes a good trade-off between vi-
sual detail and color continuity at patch boundaries: we
efficiently obtain a close-to-optimal seam placement us-
ing graph cuts optimization. We then apply a pixel-wise
color correction in the vicinity of patch boundaries with
a principled 3D extension of multi-band image blend-
ing: we achieve faultless color continuity while avoid-
ing ghosting artifacts. We demonstrate the effectiveness
of our method on two real-world large-scale scenes.
1. Introduction
Capturing, processing and displaying the visual at-
tributes, such as color, of a 3D model typically requires
to map its surface to a two-dimensional domain. Gen-
erally, it is impossible to find a global such parameter-
ization with acceptable distortion, so an atlas structure
is adopted: it consists of a partition of the surface into
connected parts (patches) and of a piecewise 2D param-
eterization (cf for example [16] and references therein).
The instantiation of this problem in the context of
image-based 3D modeling, i.e. when extracting geom-
etry and/or visual attributes from digital photographs,
has received much attention in the computer vision and
computer graphics communities.
On the one hand, the image-based case alleviates
the parameterization problem: the projective transfor-
mations from the surface to the input images constitute
natural and optimal mappings [11, 17, 19]. They avoid
image resampling and loss of visual detail, contrarily to
approaches based on other parameterizations [1, 2, 7].
On the other hand, in the image-based modeling con-
text, color discontinuities at patch boundaries (seams)
are a crucial issue, due to photometric and geometric in-
accuracies: varying lighting conditions and camera re-
sponse, non-Lambertian reflectance, imperfect camera
calibration, approximate shape, etc. Weighted averag-
ing of images in overlapping regions [2, 6, 12, 14, 17]
is not sufficient. It causes unsatisfactory ghosting
and blurring, unless the 3D model is highly accurate
(e.g. obtained by laser range scanning) and camera
calibration is tightened using image-based registration
[2, 8, 12].
Two main axes of research have been explored in
order to reduce seam visibility. The first approach is
the optimization of patch layout. Some works force
patch boundaries into regions of high negative curva-
ture [13, 18]. Others use an image fidelity term [11, 20]
to explicitly look for a partition of the surface induc-
ing minimal color discontinuities. Of particular interest
is the formulation of this problem as a Markov random
field optimization [11], for it brings powerful algorith-
mic tools into play. However, these works suffer from
the absence of per-pixel processing: they are unable to
achieve perfect color continuity.
The second improvement path is precisely pixel-wise
color correction in the vicinity of patch boundaries. A
notable work in this category is a tentative extension of
2D multi-band image splining [5] to textured 3D sur-
faces [1]. However, this work misses the importance
of an optimal patch layout, and fails to define transition
zones of distinct and adapted width for the different fre-
quency bands. As a result, it has to keep to a two-band
frequency decomposition to limit ghosting artifacts.
In this paper, we propose a novel method for creating
a high-quality seamless texture atlas from a 3D model
and a set of calibrated images. Our method upgrades the
Markov random field approach of [11] with a principled
3D extension of multi-band image blending, thereby
achieving both close-to-optimal seam placement and
faultless color continuity. We demonstrate the effective-
ness of our method on two real-world large-scale scenes
reconstructed from high-resolution images using recent