Research
I am broadly interested in the interplay between geometry and deep learning, primarily in the context of visual computing:
1) Deep learning for geometry: applying learningbased methods to problems such as shape analysis, deformation, synthesis.
2) Geometry for deep learning: using ideas from differential geometry to augment neural network training and inference; for example, solving variational problems like "what's the smoothest interpolant between two points in latent space?"


One Noise to Rule Them All: Learning a Unified Model of SpatiallyVarying Noise Patterns
Arman Maesumi, Dylan Hu, Krishi Saripalli, Vladimir G. Kim, Matthew Fisher, Sören Pirk, Daniel Ritchie
ACM Transactions on Graphics (Proceedings of SIGGRAPH), 2024
[ project page / pdf (34mb) / arXiv / code / bibtex ]
We learn a denoising diffusion model that can produce multiple types of parametrized noise functions and blend between them spatially, even without spatiallyvarying training data.


Explorable Mesh Deformation Subspaces from Unstructured 3D Generative Models
Arman Maesumi, Paul Guerrero, Vladimir G. Kim, Matthew Fisher, Siddhartha Chaudhuri, Noam Aigerman, Daniel Ritchie
SIGGRAPH Asia, 2023 (Conference Track)
[ project page / pdf (30mb) / arXiv / bibtex ]
Given a set of landmark meshes, our method extracts a 2d deformation subspace from a pretrained nonmesh 3d generative model, which facilitates exploration of continuous variations between the landmark meshes.


Triangle InscribedTriangle Picking
Arman Maesumi
The College Mathematics Journal, 2019
[ pdf (1mb) / journal / bibtex ]
The probability density function and moments (OEIS A279055) of the area of stochastically generated inscribed geometry are derived.
Preliminary findings were presented at TUMC 2017.

Renderings
In my free time, I enjoy creating 3D renderings and physical simulations using various software. More can be found here. The programs and tools that I use include: Blender, Cinema 4D, RealFlow, Vray, Octane, Arnold, Krakatoa, and more.

Click to see more
