Artificial Intelligence & Innovation
Our Research
At SFU’s School of Computing Science, artificial intelligence is driving groundbreaking research across machine learning, computer vision, computer graphics, natural language processing, robotics, knowledge representation and reasoning, constraint optimization, and intelligent systems.
Our researchers are pushing the boundaries of AI, from developing machines that understand and interpret the visual world to creating intelligent robots, learning systems, and computational tools that address complex real-world challenges.
25+
MACHINE learning faculty members
#1
IN CANADA FOR COMPUTER GRAPHICS
#1
IN CANADA FOR COMPUTER VISION
#2
IN CANADA FOR ROBOTICS
#3
IN CANADA FOR Databases
Research Collaborations
Research Spotlight
Our faculty and students are advancing AI research at SFU and beyond. Explore some of our research highlights below.
New tool brings blender-like Lighting control to any photograph
Lighting plays a crucial role when it comes to visual storytelling. Whether it’s film or photography, creators spend countless hours, and often significant budgets, crafting the perfect illumination for their shot. But once a photograph or video is captured, the illumination is essentially fixed. Adjusting it afterward, a task called “relighting,” typically demands time-consuming manual work by skilled artists.
In a new paper to be presented at this year's SIGGRAPH conference in Vancouver, researchers in the Computational Photography Lab at SFU offer a different approach to relighting. Their work, “Physically Controllable Relighting of Photographs”, brings explicit control over lights, typically available in Computer Graphics software such as Blender or Unreal Engine, to image and photo editing.
Learn more about the work: https://yaksoy.github.io/PhysicalRelighting/
PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objects
SFU PhD student Jiayi Liu has done research on modeling 3D objects with parts that move. Such interactive 3D digital twins are useful for training robotics and embodied AI in simulation, to enable reliable and safe deployment of AI assistants that can help people with everyday life.
Jiayi presented papers on this topic at top-tier international conferences (PARIS at ICCV 2023, CAGE at CVPR 2024, SINGAPO at ICLR 2025, and Artiverse at CVPR 2026). To help researchers understand this emerging area of research, Jiayi also contributed a state-of-the-art survey paper at Eurographics 2025.
Learn more about this line of work at Jiayi’s website: https://sevenljy.github.io/
New SFU study unveils AI that designs drugs and tells you how to synthesize them
SFU experts Tony Shen, Computing Science PhD student, and Martin Ester, Professor at the School of Computing Science, worked on a study, “Compositional Flows for 3D Molecule and Synthesis Pathway Co-design", that introduces an innovative method, called CGFlow.
This method tackles one of the pharmaceutical industry’s most persistent challenges: designing effective, synthesizable drug molecules by integrating cutting-edge 3D modeling with practical chemical synthesis. The study has been published at the International Conference on Machine Learning 2025, a top conference in its field.
Learn more about this study: https://arxiv.org/html/2504.08051v1