Ben Ahlbrand ☕️
Ben Ahlbrand

Senior Research Scientist

Unity

About Me

Ben Ahlbrand works at the intersection of computer graphics, machine learning, and real-time simulation / animation. Past & present collaborations include Unity Labs, Bose Research, Oculus Research, Verizon, NYU Future Reality Lab, JangaFX.

Interests
  • Computer Graphics / Vision
  • Machine Learning
  • Simulation / Animation
Education

  • MS Computer Science

    New York University - Courant Institute

  • BS Computer Science

    Purdue University - West Lafayette

📚 My Research
My most recent work is as a Senior Research Scientist at Unity Technologies at the intersection of machine learning and graphics. My work there has included applying machine learning to digital humans, generative 3D, large scale unstructured asset retrieval, and working to support Muse AI research (formerly Unity Labs). Previously, I worked with JangaFx exploring applications of machine learning to their VFX tool workflow. Before that, I spent a few years working as a Research Scientist at the Future Reality Lab (NYU Courant) with Ken Perlin where our work explored the intersection between procedural generation, machine learning and computer graphics.
Recent Publications
Kristofer Schlachter*, Benjamin Ahlbrand*, Zhu Wang, Ken Perlin, Valerio Ortenzi (2022). Zero-Shot Multi-Modal Artist-Controlled Retrieval and Exploration of 3D Object Sets. SIGGRAPH Asia 2022 Technical Communications.
PDF Cite Video DOI URL
Kris Layng, Michael Gold, Benjamin Ahlbrand, Zhenyi He, Ken Perlin (2020). The Outpost. ACM SIGGRAPH 2020 Immersive Pavilion.
Cite DOI URL
Jiawei Zhang, Abish Malik, Benjamin Ahlbrand, Niklas Elmqvist, Ross Maciejewski, David S. Ebert (2017). TopoGroups: Context-Preserving Visual Illustration of Multi-Scale Spatial Aggregates. Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems.
Cite DOI URL
Jiawei Zhang, Benjamin Ahlbrand, Abish Malik, Junghoon Chae, Zhiyu Min, Sungahn Ko, David S. Ebert (2016). A Visual Analytics Framework for Microblog Data Analysis at Multiple Scales of Aggregation. Computer Graphics Forum.
Cite DOI URL
Jieqiong Zhao, Guizhen Wang, Junghoon Chae, Hanye Xu, Siqaio Chen, William Hatton, Sherry Towers, Mahesh Babu Gorantla, Benjamin Ahlbrand, Jiawei Zhang, Abish Malik, Sungahn Ko, David S. Ebert (2015). ParkAnalyzer: Characterizing the movement patterns of visitors VAST 2015 Mini-Challenge 1. 2015 IEEE Conference on Visual Analytics Science and Technology (VAST).
Cite DOI URL
See all publications
Blog
A Scalable and Production Ready Sky and Atmosphere Rendering Technique
A Scalable and Production Ready Sky and Atmosphere Rendering Technique

I implemented a eurographics paper on rendering sky and atmospheres called "*A Scalable and Production Ready Sky and Atmosphere Rendering Technique*". Here are a few cool results: #![](/assets/atmos

Dec 12, 2024

C++ Synthesizer

check from my synthesizer [procedural sfx](

Mar 20, 2024

CPU Pathtracer
CPU Pathtracer

I wrote a monte carlo path tracer based on ray tracing in a weekend series as a stress test for my vector / matrix math library in C++. Here's some raw output: ![raw](/assets/vertopal.com_cpu_path

May 15, 2023

Tutorial: Converting VDB files to NanoVDB via OpenVDB in C++

VDB files are commonly used for storing volumetric density grids, such as clouds or smoke. Blender, Embergen, Houdini are a few sources of such data. More recently there is a sparse specification, cal

Jun 27, 2022

Quickstart: Renderdoc debugging OpenGL apps
Quickstart: Renderdoc debugging OpenGL apps

There's pretty much nothing worse in graphics programming, when you have a black screen and have no idea why. Renderdoc seeks to remedy this inability to debug the blackbox GPU APIs being interfaced w

Jun 24, 2022

See all