2014 2nd International Conference on 3D Vision 2014
DOI: 10.1109/3dv.2014.18
|View full text |Cite
|
Sign up to set email alerts
|

LETHA: Learning from High Quality Inputs for 3D Pose Estimation in Low Quality Images

Abstract: Abstract-We introduce LETHA (Learning on Easy data, Test on Hard), a new learning paradigm consisting of building strong priors from high quality training data, and combining them with discriminative machine learning to deal with lowquality test data. Our main contribution is an implementation of that concept for pose estimation. We first automatically build a 3D model of the object of interest from high-definition images, and devise from it a pose-indexed feature extraction scheme. We then train a single clas… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2015
2015
2018
2018

Publication Types

Select...
2
1
1

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(3 citation statements)
references
References 25 publications
0
3
0
Order By: Relevance
“…For this paper, we used two 3D models: The Sagrada Familia dataset (from [17]), composed of 478 images of this church in Barcelona. The resulting 3D model contains 100, 532 3D points.…”
Section: Building the 3d Modelmentioning
confidence: 99%
“…For this paper, we used two 3D models: The Sagrada Familia dataset (from [17]), composed of 478 images of this church in Barcelona. The resulting 3D model contains 100, 532 3D points.…”
Section: Building the 3d Modelmentioning
confidence: 99%
“…Whereas for the contact tools, it requires different and specific machines for every parameter to be measured, increasing the maintenance costs. In contrast, mobile laser scanning seems to be suitable in order to gather all the required data at same time, independent of lighting limitations, and providing better measurement accuracy [1]. The problem is that a methodology to classify and model the rail track from laser data did not exist up to now.…”
Section: Introductionmentioning
confidence: 99%
“…This new paradigm is sufficiently robust to be able to solve pose estimation reliably even under the hardest contexts of degraded image quality. [79] 4. Finally, we have given a new solution to the 3D object pose estimation problem for non-textured point clouds.…”
Section: Contributionsmentioning
confidence: 99%