Po Kong Lai Po Kong Lai

I'm an AI researcher with interests in the media and entertainment space.

Professional

I'm the Head of R&D at MasterpieceX, where I lead research on everything AI related. Previously I completed a PhD in Computer Science at School of Electrical Engineering and Computer Science, University of Ottawa, focusing on computer vision and machine learning. My doctoral work was under the supervision of Robert Laganière with the VIVA Research Lab.

Personal

Outside of research I'm interested in natural sciences, media analysis, and gaming. The Projects section of this site is where I put experiments in 3D graphics and interactive computing.

Based in Ottawa, Canada.

Skills & Tools

Python · PyTorch · Machine Learning · JavaScript · Three.js · WebGL · CUDA · TypeScript · C++ · C# · Unity3D · Unreal Engine · Agentic Frameworks

Links

Blog

Notes on AI, research, 3D graphics, and things I find interesting.

Loading…

← Writing

Projects

Client-side experiments in 3D graphics and interactive computing. Everything runs in the browser.

Curriculum Vitae

Education
PhD, Computer Vision & Machine Learning 2014–2019
University of Ottawa
MSc, Computational Geometry & Image Processing 2011–2013
Carleton University
BSc, Computer Science — Highest Honors 2006–2011
Carleton University
Work Experience
Head of R&D — Brinx Software Inc. (Masterpiece X) Sept 2018–Present
Ottawa, ON, Canada
  • Spearheaded 60+ R&D initiatives to modernize the 3D content creation pipeline by integrating advanced geometry processing and generative AI.
  • Conceptualized and launched MasterpieceX, a text/image driven generative AI tool for end-to-end 3D asset creation with over 130k users.
  • Designed and implemented modular agentic-based 3D content workflows integrating human oversight to boost creative output speed and quality.
  • Engineered advanced geometry processing algorithms (auto-UV unwrapping, remeshing, mesh booleans, voxelization, skeletonization, auto-rig & skin) resulting in over 80% reduction in time-to-creative output.
  • Developed cutting-edge immersive VR applications for desktop PC and Quest 2 (mesh sculpting, texture painting, rigging & skinning, 3D animation).
  • Architected, deployed and maintained 25+ containerized solutions.
  • Mentored and fostered the growth of 12 developers.
Research & Teaching Assistant — University of Ottawa Jan 2014–Sept 2019
Ottawa, ON, Canada
  • Designed and implemented a novel framework for creating immersive VR experiences from a single RGB-D sensor.
  • Developed novel methods for background/foreground separation, dynamic 3D scene reconstruction, video summarization, and ML models for omni-directional depth map generation and 3D shape completion.
  • Teaching: Discrete Structures, Introduction to Computing I (Java & Python).
Research & Teaching Assistant — Carleton University Sept 2011–Dec 2013
Ottawa, ON, Canada
  • Implemented surface parameterization algorithms for unfolding 3D meshes of tunnels for geological analysis.
  • Teaching: Discrete Mathematics, Abstract Data Types and Algorithms, Introduction to Computer Science.
Software Developer — March Networks Jan 2010–Aug 2011
Ottawa, ON, Canada
  • Core development of VideoSphere Command, an IP video management software suite.
Intern Software Developer — Corel Corporation May–Aug 2009
Ottawa, ON, Canada
  • Implemented color management features in CorelDRAW Graphics Suite X5; integrated a C# WPF asset manager into the C++ CorelDRAW environment.
Intern Software Developer — IBM May–Dec 2008
Ottawa, ON, Canada
  • Core development of J9 Java Class Libraries; added regression testing and automated execution environment management.
NSERC USRA Research Assistant — Carleton University Jan–Aug 2008
Ottawa, ON, Canada
  • Implementation of a novel image segmentation algorithm using the Well-Separated Pair Decomposition data structure.
Publications
  1. Shuang Xie, Po Kong Lai, Robert Laganiere and Jochen Lang. "Effective convolutional neural network layers in flow estimation for omni-directional images." 3DV 2019, pp. 671–680. IEEE.
  2. Po Kong Lai, Weizhe Liang and Robert Laganiere. "Additive depth maps, a compact approach for shape completion of single view depth maps." Graphical Models 104 (2019): 101030.
  3. Po Kong Lai, Shuang Xie, Jochen Lang and Robert Laganière. "Real-time panoramic depth maps from omni-directional stereo images for 6 DOF videos in virtual reality." IEEE VR 2019, pp. 405–412.
  4. Po Kong Lai and Robert Laganière. "Creating Immersive Virtual Reality Scenes Using a Single RGB-D Camera." ICIAR 2017, pp. 221–230. Springer.
  5. Po Kong Lai and Claire Samson. "Applications of mesh parameterization and deformation for unwrapping 3D images of rock tunnels." Tunnelling and Underground Space Technology 58 (2016): 109–119.
  6. Po Kong Lai, Marc Décombas, Kelvin Moutet and Robert Laganiere. "Video summarization of surveillance cameras." AVSS 2016, pp. 286–294. IEEE.
  7. Po Kong Lai, Claire Samson and Prosenjit Bose. "Visual enhancement of 3D images of rock faces for fracture mapping." International Journal of Rock Mechanics and Mining Sciences 72 (2014): 325–335.
  8. Po Kong Lai, Claire Samson and Prosenjit Bose. "Surface roughness of rock faces through the curvature of triangulated meshes." Computers & Geosciences 70 (2014): 229–238.
  9. Tara McLeod et al. "Using video acquired from an unmanned aerial vehicle (UAV) to measure fracture orientation in an open-pit mine." Geomatica 67, no. 3 (2013): 173–180.
  10. Alexandre Boivin, Po Kong Lai et al. "Electromagnetic induction sounding and 3D laser imaging in support of a Mars methane analogue mission." Planetary and Space Science 82 (2013): 27–33.
Patents
Computer animation methods and systems Granted Sept 2024
U.S. Patent No. 12,094,043 B2 · Brinx Software Inc. · Google Patents ↗
System and method for remixing 3D assets using Generative AI Pending 2025
Brinx Software Inc. · Google Patents ↗