NSER-IBVS - Presentation Website

This repository contains the source code and assets for the official project website of the paper "Efficient Self-Supervised Neuro-Analytic Visual Servoing for Real-time Quadrotor Control", presented at the ICCV 2025 Embedded Vision Workshop (Oral).

Live Website: spacetime-vision-robotics-laboratory.github.io/NSER-IBVS

Paper Summary

Authors: Sebastian Mocanu, Sebastian-Ion Nae, Mihai Eugen Barbu, Marius Leordeanu

Abstract:

We present a self-supervised neuro-analytical framework featuring a Numerically Stable Efficient and Reduced (NSER) Image-Based Visual Servoing (IBVS) teacher model. This teacher is distilled into a lightweight 1.7M parameter student network that achieves 11x real-time performance with improved control accuracy, enabling autonomous drone navigation in GPS-denied environments.

Resources

• Paper (PDF)
• arXiv
• Code
• Poster
• Dataset

Local Development

Simply open index.html in a browser, or serve with any static file server:

python -m http.server 8000

Deployment

The site auto-deploys to GitHub Pages via the included workflow .github/workflows/github-pages.yml, which handles image compression and CSS/JS minification.

Citation

@InProceedings{Mocanu_2025_ICCV,
    author    = {Mocanu, Sebastian and Nae, Sebastian-Ion and Barbu, Mihai-Eugen and Leordeanu, Marius},
    title     = {Efficient Self-Supervised Neuro-Analytic Visual Servoing for Real-time Quadrotor Control},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
    month     = {October},
    year      = {2025},
    pages     = {1744-1753}
}