---
license: gpl-3.0
tags:
- cross-modal-retrieval
- point-cloud
---

# CrossWeave: Cross-Modal Scene and Instance Retrieval from Sparse 2D-3D Alignment

**NeurIPS 2026** · Paper (coming soon) · [Project page](https://crossweave3d.github.io) · [Code](https://github.com/crossweave3d/crossweave)

| File | Image encoder | Scene R@1 ScanNet | Scene R@1 3RScan | Instance Top-1 ScanNet | Instance Top-1 3RScan |
|---|---|---|---|---|---|
| `crossweave_dinov2_vitl14.ckpt` | DINOv2 ViT-L/14 | 60.58 | 47.13 | 77.66 | 73.61 |
| `crossweave_tipsv2_l14.ckpt` | TIPSv2 ViT-L/14 | 59.29 | 43.95 | 75.22 | 73.28 |

Image → point cloud, val split. Checkpoints contain only the trained adapters and SALAD. Installation, data
preparation and evaluation are described in the [code repository](https://github.com/crossweave3d/crossweave).