Resume Email
PhD student · Indiana University · Luddy School

Mohamed Abouagour.
Computer vision & structured generative models for visual data.

Evolution had a few billion years to figure out perception, reasoning, language, and the rest of it. I’d like to skip the line. My research borrows what biology already worked out and bakes it into priors, physics-grounded models, and differentiable systems, so machines can pick up the trick without waiting another eon.

Research CV (PDF)
…
Fig. 1 — A fibre orientation distribution rendered live with a Spherical Hermite Map: 4 texture taps, bicubic Hermite reconstruction, analytic normals.
01 / research

Selected research

01 2025

ResPlan — 17K-plan vector–graph dataset

First author · Preprint · arXiv:2508.14006

A large-scale vector–graph corpus of 17,000 residential floor plans with rooms, walls, doors, windows, and the room-connectivity graph.

  • Computer vision
  • Dataset
  • Vector graphics
  • Graph learning
  • Visual parsing
Live demo arXiv:2508.14006 Plannify Studio
02 2025

GFLAN — graph-conditioned generative layouts

First author · Preprint · arXiv:2512.16275

A graph-conditioned generative model for functional 2D layouts that satisfies user-supplied topological constraints by construction.

  • Computer vision
  • Generative models
  • Graph neural networks
  • Layout synthesis
  • Structured prediction
arXiv:2512.16275 Plannify (code) Plannify Studio
03 2026

Spherical Hermite Maps

First author (with E. Garyfallidis) · Preprint · arXiv:2602.20063

A derivative-augmented cubemap that reconstructs any function on S² with bicubic-quality from a 2×2 texel footprint, with analytic surface normals.

  • Spherical representations
  • Real-time rendering
  • WebGPU / WGSL
  • Hermite interpolation
  • Spherical CNNs
Live demo arXiv:2602.20063 DIPY PR #3868
04 2026

PRISM — differentiable analysis-by-synthesis

First author (with A. Shah, E. Garyfallidis) · Preprint · arXiv:2604.00250

Couples a physics-based forward model with gradient-based optimisation to recover latent fibre structure from noisy diffusion-MRI measurements.

  • Inverse problems
  • Analysis-by-synthesis
  • Differentiable rendering
  • Diffusion MRI
  • Optimisation
arXiv:2604.00250
05 2022 –

FURY · WebGPU scientific visualisation

Core contributor & maintainer · FURY · Python Software Foundation

Core contributor and maintainer of FURY v2 — 54+ merged PRs across the WebGPU rendering core, actor primitives, and animation system.

  • Open-source research software
  • WebGPU
  • WGSL
  • Python
  • Scientific visualisation
FURY
06 2024 –

DIPY · GPU primitives for diffusion MRI

Contributor · DIPY

Contributor: Skyline ODF visualisation in DIPY Horizon (Spherical Hermite Maps) and compute-shader streamtube generation for tractography.

  • WGSL
  • Compute shaders
  • Diffusion MRI
  • Tractography
  • Open source
DIPY DIPY PR #3868
02 / dataset

ResPlan — interactive viewer

The viewer renders straight from the same .pkl released with the dataset. Toggle the typed edges (via_door, via_window, direct, adjacency) to inspect the connectivity graph that conditions GFLAN.

loading…

syn-001 · 5 rooms · 10.0 × 7.0 m

livingkitchenbedroombathhall
living kitchen bedroom bath hall door front door window
03 / teaching

Teaching, mentoring & service

  • Co-Instructor Spring 2025 & Spring 2026
    DSCI-D 321 · Data Representation (undergraduate)
    Indiana University, Luddy School

    Co-designed the curriculum; taught 150+ students time-series, Fourier, audio representations, graph theory, and the NumPy / data-engineering stack.

  • Teaching Assistant Fall 2025
    Intelligent Systems I (undergraduate)
    Indiana University, Luddy School

    Led labs and office hours on search, probabilistic reasoning, and ML fundamentals.

  • Mentor — Google Summer of Code 2024
    FURY · LLM-assisted developer tooling
    Python Software Foundation

    Mentored a contributor on integrating LLM-powered assistants with Discord, GitHub, and X for an open-source visualisation project.

  • Contributor — Google Summer of Code 2022
    FURY · keyframe animation system
    Python Software Foundation

    Built play/pause/rewind, SLERP rotation, linear and non-linear interpolation, hierarchical transforms, and motion paths.

Selected awards

  • 2025, 2026 Luddy Summer Research Fellowship — Indiana University
  • 2024 – PhD, Intelligent Systems Engineering — GPA 3.976 / 4.0 — Indiana University, Luddy School
  • 2024 Google Summer of Code — Mentor — Python Software Foundation (FURY)
  • 2022 Google Summer of Code — Contributor — Python Software Foundation (FURY)
04 / about

Short bio

I am a PhD student in Intelligent Systems Engineering at Indiana University’s Luddy School, working in the Garyfallidis Research Group since August 2024. My research lives at the intersection of computer vision, structured generative modelling, and real-time GPU rendering: large-scale visual datasets (ResPlan), graph-conditioned generators (GFLAN), differentiable analysis-by-synthesis (PRISM), and mesh-free spherical primitives (Spherical Hermite Maps).

I co-instruct DSCI-D 321 (Data Representation), TA Intelligent Systems I, and mentor for Google Summer of Code (2024 mentor, 2022 contributor). I am a core maintainer of FURY v2 (54+ merged PRs) and a contributor to DIPY, where I shipped the Skyline ODF renderer and a compute-shader streamtube generator for tractography. I hold a BEng in Electrical Engineering (Computer Engineering & Automatic Control) from Tanta University, Egypt.

  • Program PhD, Intelligent Systems Engineering (Aug 2024 – present)
  • Advisor Eleftherios Garyfallidis
  • Datasets ResPlan (17K vector–graph plans)
  • Models GFLAN · PRISM · graph & physics priors
  • Rendering Spherical Hermite Maps · WGSL · WebGPU
  • Stack PyTorch · Python · TypeScript · CUDA · WGSL
  • Mentoring GSoC 2024 (FURY) · GSoC 2022 contributor
06 / contact

Get in touch

Open to PhD-lab collaborations, reading-group invitations, and research conversations. The fastest line is email.