Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors
2019 ◽
Vol 33
◽
pp. 8409-8416
◽
Keyword(s):
We present a method to infer 3D pose and shape of vehicles from a single image. To tackle this ill-posed problem, we optimize two-scale projection consistency between the generated 3D hypotheses and their 2D pseudo-measurements. Specifically, we use a morphable wireframe model to generate a fine-scaled representation of vehicle shape and pose. To reduce its sensitivity to 2D landmarks, we jointly model the 3D bounding box as a coarse representation which improves robustness. We also integrate three task priors, including unsupervised monocular depth, a ground plane constraint as well as vehicle shape priors, with forward projection errors into an overall energy function.
2020 ◽
Vol V-2-2020
◽
pp. 451-458
Keyword(s):
Keyword(s):
2020 ◽
Vol 34
(07)
◽
pp. 11661-11668
◽
Keyword(s):
2018 ◽
Vol 7
(02)
◽
pp. 23578-23584
Keyword(s):
Keyword(s):
2020 ◽
Vol 2020
(14)
◽
pp. 377-1-377-7
Keyword(s):