5 papers
Neural Particle Automata: Learning Self-Organizing Particle Dynamics
Hyunsoo Kim, Ehsan Pajouheshgar, Sabine Süsstrunk +2
We introduce Neural Particle Automata (NPA), a Lagrangian generalization of Neural Cellular Automata (NCA) from static lattices to dynamic particle systems. Unlike classical Euleri…
Neural Cellular Automata: From Cells to Pixels
Ehsan Pajouheshgar, Yitao Xu, Ali Abbasi +3
Neural Cellular Automata (NCAs) are bio-inspired dynamical systems in which identical cells iteratively apply a learned local update rule to self-organize into complex patterns, ex…
Exploring the Landscape of Non-Equilibrium Memories with Neural Cellular Automata
Ehsan Pajouheshgar, Aditya Bhardwaj, Nathaniel Selub +1
We investigate the landscape of many-body memories: families of local non-equilibrium dynamics that retain information about their initial conditions for thermodynamically long tim…
Canonical Latent Representations in Conditional Diffusion Models
Yitao Xu, Tong Zhang, Ehsan Pajouheshgar +1
Conditional diffusion models (CDMs) have shown impressive performance across a range of generative tasks. Their ability to model the full data distribution has opened new avenues f…
Volumetric Temporal Texture Synthesis for Smoke Stylization using Neural Cellular Automata
Dongqing Wang, Ehsan Pajouheshgar, Yitao Xu +2
Artistic stylization of 3D volumetric smoke data is still a challenge in computer graphics due to the difficulty of ensuring spatiotemporal consistency given a reference style imag…