Conditional Generative Models for Implicit Plant Growth modeling.

Created in March 26, 2023

2023   ·   computer-vision,   5-minutes-or-less   ·   seminar

Abstract — Recent developments in computer vision and deep learning have led to powerful methods for generating new images within a specified domain such as human faces or plants. One such model is the Variational Autoencoder (VAE). This generative architecture allows us to implicitly model and sample the probability distribution of a latent space that describes the domain to generate new images. Conditional Variational Autoencoders (CVAE) are a variant of the VAE that allows us to constrain our model to specified attributes. We can leverage the power of these generative models towards the domain plant modeling. Can we predict what a plant will look like in the latter stages with only a sequence of images of the plant in the early stages? We explore this question further in the presentation.

Presentation:



If you found this useful, please cite this as:

Debbagh, Mohamed (Mar 2023). Conditional Generative Models for Implicit Plant Growth modeling.. https://mohas95test.github.io/.

or as a BibTeX entry:

@article{debbagh2023conditional-generative-models-for-implicit-plant-growth-modeling,
  title   = {Conditional Generative Models for Implicit Plant Growth modeling.},
  author  = {Debbagh, Mohamed},
  year    = {2023},
  month   = {Mar},
  url     = {https://mohas95test.github.io//lectures/2023/PhDSeminar1/}
}


Enjoy Reading This Article?

Here are some more articles you might like to read next:

  • Simulation and Modeling for Digital Plant Growth Representations.
  • Introduction to Compuational Photography and Computer Vision
  • Introductory Robotics Tutorials
  • Capacitors/ Inductors
  • Neural Radiance Fields (NeRFs): A Review and Some Recent Developments.