Research
I am interested in the applications of machine learning methods for representing, synthesizing, and manipulating 3D objects and scenes.
|
|
One Noise to Rule Them All: Learning a Unified Model of Spatially-Varying 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 / bibtex ]
We learn a denoising diffusion model that can produce multiple types of parametrized noise functions and blend between them spatially, even without spatially-varying 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 2-d deformation subspace from a pretrained non-mesh 3-d generative model, which facilitates exploration of continuous variations between the landmark meshes.
|
|
Learning Transferable 3D Adversarial Cloaks for Deep Trained Detectors
Arman Maesumi*, Mingkang Zhu*, Yi Wang, Tianlong Chen, Zhangyang Wang, Chandrajit Bajaj
arXiv, 2021
[ pdf (8mb) / arXiv / bibtex ]
3D human meshes are cloaked from object detectors via adversarial texture maps, which are trained using differentiable rendering.
|
|
Triangle Inscribed-Triangle 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
|