# Zoo3D: Zero-Shot 3D Object Detection at Scene Level

**Date:** 2026-02-20

M:3L researchers co-authored Zoo3D, accepted at [CVPR 2026](https://openaccess.thecvf.com/content/CVPR2026/html/Lemeshko_Zoo3D_Zero-Shot_3D_Object_Detection_at_Scene_Level_CVPR_2026_paper.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). The work introduces the first training-free, open-vocabulary 3D object detector: it clusters 2D instance masks across views into class-agnostic 3D boxes, then labels them through best-view selection and view-consensus visual-language matching. Zoo3D supports point clouds as well as posed or unposed RGB images, while its zero-shot and self-supervised variants deliver leading results on ScanNet200 and ARKitScenes.

## Related links

- [Read the paper](https://arxiv.org/abs/2511.20253)
- [Official CVPR record](https://openaccess.thecvf.com/content/CVPR2026/html/Lemeshko_Zoo3D_Zero-Shot_3D_Object_Detection_at_Scene_Level_CVPR_2026_paper.html)
- [View code](https://github.com/col14m/zoo3d)
- [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/zoo3d-cvpr-2026)
- [All M:3L news and events](https://m3l.am/news.md)