TY - JOUR
T1 - Distinction of 3D Objects and Scenes via
Classification Network and Markov Random Field
AU - Song, Ran
AU - Liu, Yonghuai
AU - Rosin, Paul L
PY - 2020/6/1
Y1 - 2020/6/1
N2 - An importance measure of 3D objects inspired by human perception has a range of applications since people want
computers to behave like humans in many tasks. This paper revisits a well-defined measure, distinction of 3D surface mesh, which
indicates how important a region of a mesh is with respect to classification. We develop a method to compute it based on a
classification network and a Markov Random Field (MRF). The classification network learns view-based distinction by handling multiple
views of a 3D object. Using a classification network has an advantage of avoiding the training data problem which has become a major
obstacle of applying deep learning to 3D object understanding tasks. The MRF estimates the parameters of a linear model for
combining the view-based distinction maps. The experiments using several publicly accessible datasets show that the distinctive
regions detected by our method are not just significantly different from those detected by methods based on handcrafted features, but
more consistent with human perception. We also compare it with other perceptual measures and quantitatively evaluate its
performance in the context of two applications. Furthermore, due to the view-based nature of our method, we are able to easily extend
mesh distinction to 3D scenes containing multiple objects.
AB - An importance measure of 3D objects inspired by human perception has a range of applications since people want
computers to behave like humans in many tasks. This paper revisits a well-defined measure, distinction of 3D surface mesh, which
indicates how important a region of a mesh is with respect to classification. We develop a method to compute it based on a
classification network and a Markov Random Field (MRF). The classification network learns view-based distinction by handling multiple
views of a 3D object. Using a classification network has an advantage of avoiding the training data problem which has become a major
obstacle of applying deep learning to 3D object understanding tasks. The MRF estimates the parameters of a linear model for
combining the view-based distinction maps. The experiments using several publicly accessible datasets show that the distinctive
regions detected by our method are not just significantly different from those detected by methods based on handcrafted features, but
more consistent with human perception. We also compare it with other perceptual measures and quantitatively evaluate its
performance in the context of two applications. Furthermore, due to the view-based nature of our method, we are able to easily extend
mesh distinction to 3D scenes containing multiple objects.
KW - 3D mesh
KW - Markov random field
KW - distinction
KW - neural network
UR - http://www.scopus.com/inward/record.url?scp=85058141711&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85058141711&partnerID=8YFLogxK
UR - https://www.mendeley.com/catalogue/c4e49013-05a5-3e22-8e2b-d08b4b6f1048/
U2 - 10.1109/TVCG.2018.2885750
DO - 10.1109/TVCG.2018.2885750
M3 - Article (journal)
SN - 1077-2626
VL - 26
SP - 2204
EP - 2218
JO - IEEE Transactions on Visualization and Computer Graphics
JF - IEEE Transactions on Visualization and Computer Graphics
IS - 6
M1 - 8567954
ER -