# CoViS-Net: A Cooperative Visual Spatial Foundation Model for Multi-Robot Applications

arXiv: https://arxiv.org/abs/2405.01107 · HTML: https://mlsanity.com/paper/2405.01107/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 May 2024.

## Built on by (most cited first, 5 of 5)

- [A Likelihood Ratio-Based Approach to Segmenting Unknown Objects](https://mlsanity.com/paper/2409.06424/) (2024)
- [Robust Bird's Eye View Segmentation by Adapting DINOv2](https://mlsanity.com/paper/2409.10228/) (2024)
- [BEVCon: Advancing Bird's Eye View Perception with Contrastive Learning](https://mlsanity.com/paper/2508.04702/) (2025)
- [G2G: Exploiting Intra-Group Geometry for Inter-Group Pose Estimation](https://mlsanity.com/paper/2606.08284/) (2026)
- [ConPoSe: LLM-Guided Contact Point Selection for Scalable Cooperative Object Pushing](https://mlsanity.com/paper/2510.08705/) (2025)

## Abstract (arXiv)

Autonomous robot operation in unstructured environments is often underpinned by spatial understanding through vision. Systems composed of multiple concurrently operating robots additionally require access to frequent, accurate and reliable pose estimates. In this work, we propose CoViS-Net, a decentralized visual spatial foundation model that learns spatial priors from data, enabling pose estimation as well as spatial comprehension. Our model is fully decentralized, platform-agnostic, executable in real-time using onboard compute, and does not require existing networking infrastructure. CoViS-Net provides relative pose estimates and a local bird's-eye-view (BEV) representation, even without camera overlap between robots (in contrast to classical methods). We demonstrate its use in a multi-robot formation control task across various real-world settings. We provide code, models and supplementary material online. https://proroklab.github.io/CoViS-Net/