|
This article introduces three-filters-to-normal+
(3F2N+), an extension of our previous work three-filtersto-
normal (3F2N), with a specific focus on incorporating
discontinuity discrimination capability into surface normal estimators
(SNEs). 3F2N+ achieves this capability by utilizing
a novel discontinuity discrimination module (DDM), which
combines depth curvature minimization and correlation coefficient
maximization through conditional random fields (CRFs).
To evaluate the robustness of SNEs on noisy data, we create
a large-scale synthetic surface normal (SSN) dataset containing
20 scenarios (ten indoor scenarios and ten outdoor scenarios with
and without random Gaussian noise added to depth images).
Extensive experiments demonstrate that 3F2N+ achieves greater
performance than all other geometry-based surface normal
estimators, with average angular errors of 7.85◦, 8.95◦, 9.25◦,
and 11.98◦ on the clean-indoor, clean-outdoor, noisy-indoor, and
noisy-outdoor datasets, respectively. We conduct three additional
experiments to demonstrate the effectiveness of incorporating
our proposed 3F2N+ into downstream robot perception tasks,
including freespace detection, 6D object pose estimation, and
point cloud completion. Our source code and datasets are publicly
available at https://mias.group/3F2Nplus/.
|
