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

Navigate this page
Awards  /  Publications  /  News

profile photo
Awards 🏆

Dec. 2023 Teaching Assistance Excellence Award From EPFL
Aug. 2022 Best Paper Award From SIGGRAPH 2022 Conference
Oct. 2020 Doctoral Fellowship from EDIC EPFL
Sept. 2019 Gold Medal in Iranian National Statistics Olympiad
Aug. 2014 Gold Medal in Iranian National Physics Olympiad



Publication Highlights 📜
Mesh Neural Cellular Automata
Ehsan Pajouheshgar*, Yitao Xu*, Alexander Mordvintsev, Eyvind Niklasson, Tong Zhang, Sabine Süsstrunk
SIGGRAPH, 2024
Demo / arXiv / code

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!

NoiseNCA: Noisy Seed Improves Spatio-Temporal Continuity of Neural Cellular Automata
Ehsan Pajouheshgar, Yitao Xu, Sabine Süsstrunk
Artificial Life (ALife), 2024
Demo / arXiv / Coming soon

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!

DyNCA: Real-time Dynamic Texture Synthesis Using Neural Cellular Automata
Ehsan Pajouheshgar*, Yitao Xu*, Tong Zhang, Sabine Süsstrunk
CVPR, 2023
Demo / arXiv / code

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

CLIPasso: Semantically-Aware Object Sketching
Yael Vinker, Ehsan Pajouheshgar, Jessica Y. Bo, Roman Bachmann,
Amit Haim Bermano, Daniel Cohen-Or, Amir Zamir, Ariel Shamir
SIGGRAPH, 2022 (Best Paper Award)
Project Page / Demo / arXiv / code

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



Publications 📜
Emergent Dynamics in Neural Cellular Automata
Yitao Xu, Ehsan Pajouheshgar, Sabine Süsstrunk
Artificial Life (ALife), 2024
arXiv / Coming Soon

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.

Optimizing Latent Space Directions For GAN-based Local Image Editing
Ehsan Pajouheshgar, Tong Zhang, Sabine Süsstrunk
ICASSP, 2022
arXiv / code

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.

Back to square one: probabilistic trajectory forecasting without bells and whistles
Ehsan Pajouheshgar, Christoph H. Lampert
NeurIPS 2018, (Workshop on Modeling and Decision-Making in the Spatiotemporal Domain)
arXiv

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.

News 📰

July. 2024 I will attend Siggraph 2024 Conference (🤞 on visa). Let's meet there!
July. 2024 I will attend Artificial Life (ALife 2024) Conference. Let's meet there!
May. 2023 Two papers accepted to ALife 2024.
Mar. 2023 MeshNCA was accepted as a journal paper to SIGGRAPH 2024.


Webpage Template