3D Object Registration from Color Images
Vincent Lepetit
(U. of Bordeaux, France)
Abstract:
I will describe our current approach to 3D object detection and pose estimation
from color images only. We first introduce a "holistic" approach that relies on
a representation of a 3D pose suitable to Deep Networks and on a feedback loop.
This approach, like many previous ones is however not sufficient for handling
objects with an axis of rotational symmetry, as the pose of these objects is in
fact ambiguous. We show how to relax this ambiguity with a combination of
classification and regression. I will then show how we tackle the domain gap
between real images and synthetic images, in order to use synthetic images to
train our models. Finally, I will present our recent extension to deal with
large partial occlusions.
Short Bio:
Dr. Vincent Lepetit is a Full Professor at the LaBRI, University of Bordeaux.
He also supervizes a research group in Computer Vision for Augmented Reality at
theInstitute for Computer Graphics and Vision, TU Graz. He received the PhD
degree in Computer Vision in 2001 from the University of Nancy, France, after
working in the ISA INRIA team. He then joined the Virtual Reality Lab at EPFL
as a post-doctoral fellow and became a founding member of the Computer Vision
Laboratory. He became a Professor at TU Graz in February 2014, and at
University of Bordeaux in January 2017. His research is at the interface
between Machine Learning and 3D Computer Vision, with application to 3D hand
pose estimation, feature point detection and description, and 3D object and
camera registration from images. In particular, he introduced with his
colleagues methods such as Ferns, BRIEF, LINE-MOD, and DeepPrior for feature
point matching and 3D object recognition.