Add model card

README.md

@@ -0,0 +1,106 @@
+---
+license: cc-by-nc-4.0
+tags:
+- pose-estimation
+- relative-pose-estimation
+- multi-view
+- computer-vision
+- robotics
+---
+
+# G2G: Exploiting Intra-Group Geometry for Inter-Group Pose Estimation
+
+<p align="center">
+  <a href="https://weiyufei0217.github.io/G2G/"><b>🌐 Project Page</b></a>
+  &nbsp;&nbsp;|&nbsp;&nbsp;
+  <a href="https://arxiv.org/abs/2606.08284"><b>📄 arXiv</b></a>
+  &nbsp;&nbsp;|&nbsp;&nbsp;
+  <a href="https://github.com/WeiYuFei0217/G2G"><b>💻 Code (GitHub)</b></a>
+</p>
+
+> Recovering the relative 6-DoF pose between two image groups underlies cross-sequence relocalization, multi-camera rig odometry, and other multi-view tasks. Each group carries **known intra-group geometry** from a pre-built map, odometry, or rig calibration, and pretrained multi-view backbones already fuse such geometry into visual features. Yet current models treat all views as an unstructured set, leaving **cross-group reasoning** as the missing piece.
+>
+> G2G keeps a multi-view foundation model entirely frozen and adds three lightweight trainable modules (32M parameters, under 6% of the full model) to bridge the two groups: a perceiver resampler, a cross-group bridge with merged self-attention, and a multi-frame pose head. Supervised only by relative poses, G2G attains state-of-the-art accuracy on both tasks across four datasets.
+
+This repository hosts the **released artifacts** for the paper. **Code, installation, and full usage live on GitHub:** https://github.com/WeiYuFei0217/G2G
+
+## Contents
+
+| Path | Description |
+|------|-------------|
+| `release_weights/*.pth` | 10 pretrained **G2G-only** weights (frozen MapAnything backbone excluded; each ~123 MB) |
+| `examples.zip` | Sanity-check input bundles (`reloc/` + `rig/`); unzip into the repo root → `examples/` |
+| `eval_results.zip` | Paper-subset per-pair evaluation CSVs; unzip into the repo root → `eval_results/` |
+
+> The frozen MapAnything backbone (DINOv2-large / 1024-dim, MapAnything **v1.0.1**, commit `fde8425`) is **not** redistributed here. See the GitHub README, Installation step 2, for how to obtain the exact compatible backbone. The current `facebook/map-anything` Hugging Face weights are the newer giant/1536 variant and are **incompatible** with these G2G modules.
+
+## Pretrained weights
+
+| Weight | Task | Dataset |
+|--------|------|---------|
+| `HM3D-Reloc.pth` | Reloc | HM3D |
+| `TartanGround-Reloc.pth` | Reloc | TartanGround |
+| `NCLT-Reloc.pth` | Reloc | NCLT |
+| `ZJH-Reloc.pth` | Reloc | ZJH |
+| `HM3D-Rig-8.pth` | Rig | HM3D (8-cam) |
+| `HM3D-Rig-4.pth` | Rig | HM3D (4-cam) |
+| `TartanGround-Rig-4.pth` | Rig | TartanGround (4-cam) |
+| `NCLT-Rig-Intra.pth` | Rig | NCLT intra-season (5-cam) |
+| `NCLT-Rig-Cross.pth` | Rig | NCLT cross-season (5-cam) |
+| `ZJH-Rig-4.pth` | Rig | ZJH (4-cam) |
+
+These are G2G-only weights (frozen backbone excluded). The evaluation scripts in the GitHub repo automatically handle partial loading.
+
+## Download
+
+Grab a single weight:
+
+```python
+from huggingface_hub import hf_hub_download
+
+ckpt = hf_hub_download(
+    repo_id="feixue22/G2G",
+    filename="release_weights/HM3D-Reloc.pth",
+)
+print(ckpt)
+```
+
+Or pull everything (weights + example/eval bundles):
+
+```python
+from huggingface_hub import snapshot_download
+
+local_dir = snapshot_download(repo_id="feixue22/G2G")
+print(local_dir)
+```
+
+## Usage
+
+These weights plug into the G2G code on GitHub. After cloning and installing
+(https://github.com/WeiYuFei0217/G2G), run evaluation with the downloaded checkpoint:
+
+```bash
+python scripts/eval_reloc.py \
+    --config configs/reloc/hm3d.yaml \
+    --checkpoint release_weights/HM3D-Reloc.pth \
+    --output-dir outputs/eval_HM3D-Reloc \
+    --batch-size 16 --min-overlap 0.1
+```
+
+## License
+
+[CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/).
+
+## Citation
+
+```bibtex
+@misc{wei2026g2gexploitingintragroupgeometry,
+      title={G2G: Exploiting Intra-Group Geometry for Inter-Group Pose Estimation},
+      author={Yufei Wei and Shuhao Ye and Chenxiao Hu and Yiyuan Pan and Dongyu Feng and Rong Xiong and Yue Wang and Yanmei Jiao},
+      year={2026},
+      eprint={2606.08284},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2606.08284},
+}
+```