Cargando…
Event Collapse in Contrast Maximization Frameworks
Contrast maximization (CMax) is a framework that provides state-of-the-art results on several event-based computer vision tasks, such as ego-motion or optical flow estimation. However, it may suffer from a problem called event collapse, which is an undesired solution where events are warped into too...
Autores principales: | Shiba, Shintaro, Aoki, Yoshimitsu, Gallego, Guillermo |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9315985/ https://www.ncbi.nlm.nih.gov/pubmed/35890869 http://dx.doi.org/10.3390/s22145190 |
Ejemplares similares
-
Visual Odometry with an Event Camera Using Continuous Ray Warping and Volumetric Contrast Maximization
por: Wang, Yifu, et al.
Publicado: (2022) -
On the collapsibility of measures of effect in the counterfactual causal framework
por: Huitfeldt, Anders, et al.
Publicado: (2019) -
Contrasting catastrophic eruptions predicted by different intrusion and collapse scenarios
por: Rincón, M., et al.
Publicado: (2018) -
Optical Flow Estimation by Matching Time Surface with Event-Based Cameras
por: Nagata, Jun, et al.
Publicado: (2021) -
A Maximal Correlation Framework for Fair Machine Learning
por: Lee, Joshua, et al.
Publicado: (2022)