Login
Prof. Dr. Daniel Cremers
Fakultät für Informatik, TU München
The reconstruction of the 3D world from images is among the central challenges in computer
vision. Starting in the 2000s, researchers have pioneered algorithms which can reconstruct
camera motion and sparse feature-points in real-time. In my talk, I will introduce direct methods
for camera tracking and 3D reconstruction which do not require feature point estimation, which
exploit all available input data and which recover dense or semi-dense geometry rather than
sparse point clouds. They lead to a drastic boost in precision and robustness. Furthermore, I will
showcase some applications ranging from 3D photography and 3D television to autonomous
navigation.
Kosten
-
Teilnehmer 1 (ein Mann und keine Frauen )
Max. Teilnehmer Keine Teilnehmerbegrenzung
Max. Begleitpersonen 1
Zum Event anmelden
