~/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 introduce Neural Particle Automata, a Lagrangian generalization of Neural Cellular Automata where each cell is a particle with a continuous position and internal state, using differentiable SPH operators and memory-efficient CUDA kernels to scale learned self-organizing particle dynamics.
We pair a coarse-grid Neural Cellular Automata model with a lightweight implicit decoder that maps cell states and local coordinates to appearance, enabling self-organizing NCA outputs to render at arbitrary resolution in real time while preserving regeneration, robustness, and spontaneous dynamics across 2D, 3D, and mesh domains.
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.