# TUN3D: Towards Real-World Scene Understanding from Unposed Images

**Date:** 2026-01-31

M:3L researchers co-authored TUN3D, accepted at [ICRA 2026](https://ras.papercept.net/conferences/conferences/ICRA26/program/ICRA26_ContentListWeb_3.html), a [CORE 2023 A*-ranked conference](https://portal.core.edu.au/conf-ranks/?by=rank&page=1&search=A%2A&sort=atitle&source=CORE2023). It is the first system to jointly estimate room layouts and detect 3D objects in real scans from multi-view images without ground-truth camera poses or depth supervision. A lightweight sparse-convolutional backbone feeds dedicated detection and parametric wall-layout heads, enabling one model to work with point clouds, posed images, or fully unposed RGB captures and substantially advancing holistic indoor-scene understanding.

## Related links

- [Read the paper](https://arxiv.org/abs/2509.21388)
- [Official ICRA program record](https://ras.papercept.net/conferences/conferences/ICRA26/program/ICRA26_ContentListWeb_3.html)
- [View code](https://github.com/col14m/tun3d)
- [CORE 2023 ranking](https://portal.core.edu.au/conf-ranks/?by=rank&page=1&search=A%2A&sort=atitle&source=CORE2023)

## Authoritative URLs

- [Canonical news page](https://m3l.am/news/tun3d-icra-2026)
- [All M:3L news and events](https://m3l.am/news.md)