About Me

I’m a computer science researcher working at the intersection of 3D reconstruction and human-centered design. My current work focuses on demoConstruct, an open-source platform for real-time scene capture, editing, and collaboration across web and VR. The system integrates SLAM, digital twins, and collaborative 3D editing, and has been showcased at SIGGRAPH 2024 Labs and CHI 2025 Interactivity.

Earlier in my academic journey, my PhD research focused on multi-view stereo and the application of metaheuristic optimization to address ill-posed problems in multi-view geometry. This foundation in 3D reconstruction and computer vision now informs my efforts on building practical, interactive, and user-facing systems.

I’m particularly interested in:

3D reconstruction (Photogrammetry, SLAM, Gaussian Splatting)
Interactive spatial tools for web and VR (Babylon.js, WebXR)
Translational research bridging academic methods with real-world applications

Professional Experience

Research Fellow

Centre for Immersification, Singapore Institute of Technology
May 2023 - Present (2 years, 2 months)

Co-developed an open-source platform for real-time progressive 3D reconstruction and collaborative scene editing in web and VR
Evaluated and integrated MVS, SLAM, and Gaussian Splatting algorithms to enhance system capabilities
Delivered technical presentations and live demos to external stakeholders, leading to an industry collaboration
Published co-authored work at respected peer-reviewed research venues

Projects

demoConstruct

SLAM, Gaussian Splatting | Python, Babylon.js, WebXR

Co-developed an open-source platform for real-time progressive 3D reconstruction and collaborative scene editing
Integrated 3D Gaussian Splatting to improve scene realism
Showcased at SIGGRAPH 2024 Labs and CHI 2025 Interactivity

Multi-View Stereo Reconstruction

3D Reconstruction, Computer Vision, Graph Cuts, Metaheuristic Optimization | Python, MATLAB

Developed depth map-based multi-view stereo methods for 3D reconstruction
Explored the use of metaheuristics in solving multi-view geometry problems
Published research in peer-reviewed international journals and conferences

Publications

Collaborative Scene Authoring with Near Real-Time 3D Reconstruction

Leon Foo, Nirmal S. Nair, Liuziyi Liu, Jeannie Su Ann Lee, Songjia Shen, Indriyati Atmosukarto, Alvin Chan, Jing Shi, Yong Joo Loh, Yih Yng Ng, Michael Chia, Chek Tien Tan
ACM CHI 2025 Interactivity (Yokohama, Japan)
https://dl.acm.org/doi/abs/10.1145/3706599.3721190

demoConstruct: Democratizing Scene Construction for Digital Twins through Progressive Reconstruction

Leon Foo, Chek Tien Tan, Liuziyi Liu, Nirmal S. Nair, Songjia Shen, Jeannie Lee
ACM SIGGRAPH 2024 Labs (Denver, CO, USA)
https://dl.acm.org/doi/abs/10.1145/3641236.3664424

Multi-View Stereo Using Graph Cuts-Based Depth Refinement

Nirmal S. Nair and Madhu S. Nair
IEEE Signal Processing Letters, 2022
https://doi.org/10.1109/LSP.2022.3201778

Multi-view Stereo using Cross-view Depth Map Completion and Row-column Depth Refinement

Nirmal S. Nair and Madhu S. Nair
International Conference on Digital Image Processing, ICDIP 2021 (Singapore)
https://doi.org/10.1117/12.2601119

Scalable Multi-view Stereo using CMA-ES and Distance Transform-based Depth Map Refinement

Nirmal S. Nair and Madhu S. Nair
International Conference on Machine Vision, ICMV 2020 (Rome, Italy)
https://doi.org/10.1117/12.2587241

On Evolutionary Computation Techniques for Multi-view Triangulation

Nirmal S. Nair, Madhu S. Nair
Machine Vision and Applications, 2020
https://link.springer.com/article/10.1007/s00138-020-01077-2

Nirmal S. Nair