~/ehsan pajouheshgar
// postdoctoral researcher · epfl
I am a Postdoctoral Researcher at EPFL IVRL and the Chair of Statistical Field Theory. My research sits at the intersection of Self-Organizing Systems, Computer Vision, Computer Graphics, and Artificial Life — exploring how simple local rules give rise to complex global behavior. I did my PhD at EPFL (supervised by Sabine Süsstrunk) and my undergraduate at Sharif University of Technology (Computer Engineering + Math minor).
what's new
selected publications
We study binary 2D cellular automata that robustly store one-bit memories under noise, and use a modified Neural Cellular Automata framework to discover many new memory-preserving rules beyond Toom's rule.
We analyze NCA texture models in the continuous space-time limit, show that standard training overfits discretization near the seed, and use uniform-noise initialization to learn dynamics that stay consistent across resolutions, are robust to stochastic updates and additive noise, and behave like PDEs.
DyNCA enables real-time and controllable dynamic texture synthesis, producing arbitrarily long and arbitrary-size video textures while improving synthesis speed and quality by orders of magnitude over prior optimization-based methods.