Ehsan Pajouheshgar

I am currently a 4th year PhD candidate at EPFL Lausanne pursuing my doctoral studies under supervision of Sabine Süsstrunk at Image and Visual Representation Laboratory (IVRL) . Before joining EPFL, I did my bachelor's degree at Sharif University of Technology in Iran majoring in Computer Engineering and a minor in Mathematics.

My research in the last years has been focused on studying Neural Cellular Automata (NCA) models. NCAs demonstrate how self-organization and complexity can emerge from simple local interactions. The advantage of NCAs over traditional Cellular Automata is that they are differentiable and can be trained with gradient-based methods. I'm also interested in Computer Vision and Computer Graphics. I like to design (bio and physics)-inspired models to tackle different problems in these fields. More recently, I am learning and doing research on Artificial Life. I am interested in the emergence of life-like behaviors such as Solitons, Self-Organization, and Self-Replication.

Email  /  CV  /  Google Scholar  /  Github  /  Twitter

Navigate this page

Awards  /  Publications  /  News

MeshNCA is a type of Neural Cellular Automata that can operate on cells arranged on a 3D mesh. MeshNCA can simultaneously generate multiple textures (albedo, normal, roughness, ...) for Physically-based-rendering (PBR). It also enables grafting multiple NCA models on each other to create mixture of textures. Checkout the demo!

We propose a small change to Neural Cellular Automata (NCA) and show that the update rule learned by NoiseNCA actually correspond to a continuous space-time Partial Differential Equation (PDE). Utilizing this emergent space-time continuity, NoiseNCA allows changing the speed of the pattern formation and the scale of the patterns at inference time. Checkout the demo!

Dynamic Neural Cellular Automata (DyNCA), is a method that enables real-time and controllable dynamic texture synthesis. Checkout the demo!

Our work converts an image of an object to a sketch, allowing for varying levels of abstraction, while preserving its key visual features.

Trained Neural Cellular Automata (NCA) models exhibit many emergent behaviors, such as self-organization, and spontaneous motion. In this paper we investigate the spontaneous motion property of NCAs. We find that the ratio between the number of channels in the cell state and the number of hidden neurons in the update rule is a key factor that controls the NCA stability and emergent motion in the NCA generated patterns.

We introduce the Locally Effective Latent Space Direction (LELSD) framework, a novel approach to localized image editing in Generative Adversarial Networks (GANs), which utilizes a new objective function incorporating supervision from a pre-trained segmentation network.

We present an uncomplicated non-parametric baseline that attains the lowest error based on a widely adopted metric within the field. This serves to demonstrate the misleading nature of this particular metric.

Webpage Template