SUNY Korea · Stony Brook University● Graduate positions open

Computer vision / Robotics / Machine learning

Machines that
understand space.

We develop computer vision and robotics systems that perceive, reconstruct, and collaborate within the 3D world.

Directed by Prof. François Rameau ↗

BMVC 2026 logo

Publication

3DiffGS accepted to BMVC 2026

Our paper, ‘3DiffGS: 3D Gaussian Splats from Unposed 2D Images using Diffusion Models,’ has been accepted to BMVC 2026. Congratulations to Abhigyan and the entire NAAMII team behind this project!
Latest from SILAll news ↗

01 / Research

Research
directions.

Scene-coordinate regression privacy reconstruction
01

3D Vision & Localization

Recovering geometry and camera pose from visual observations, with robust and privacy-aware representations of place.

3D vision · Visual localization
Multiple connected cars collaborating on visual localization
02

Connected Robotics

Enabling autonomous agents to perceive, communicate, and collaborate in shared and changing environments.

Robotics · Multi-agent systems
Visual learning from multi-camera CCTV footage
03

Learning for Visual Systems

Reliable visual learning for domain adaptation, matching, omnidirectional imaging, and automotive applications.

Deep learning · Visual perception

02 / Latest output

Recent
publications.