README.md

---
license: mit
library_name: pytorch
pipeline_tag: image-segmentation
tags:
  - 3d-instance-segmentation
  - scannetpp
  - scannet
  - competitorformer
---

# CompetitorFormer

> **CompetitorFormer: Mitigating Query Conflicts for 3D Instance Segmentation via Competitive Strategy (CVPR 2026)**
>
> Duanchu Wang, Junjie Yang, Haoran Gong, Jing Liu, Di Wang
>
> [[Paper](https://openaccess.thecvf.com/content/CVPR2026/html/Wang_CompetitorFormer_Mitigating_Query_Conflicts_for_3D_Instance_Segmentation_via_Competitive_CVPR_2026_paper.html)]
> [[Code](https://github.com/DuanchuWang/CompetitorFormer)]

Official checkpoints for CompetitorFormer, a competitive-strategy-based transformer that mitigates query conflicts for 3D instance segmentation.

## Results & Models

### ScanNet++ (official 50-scene val)

- Model: CompetitorFormer on ScanNet++ official 50-scene val
- Checkpoint: [`competitorformer_scannetpp.pth`](https://huggingface.co/WangDuanchu/CompetitorFormer/resolve/main/competitorformer_scannetpp.pth) (`num_query=500`)
- AP / AP<sub>50</sub> / AP<sub>25</sub> = **0.339 / 0.485 / 0.581**

```bash
mkdir -p checkpoints
wget https://huggingface.co/WangDuanchu/CompetitorFormer/resolve/main/competitorformer_scannetpp.pth \
  -O checkpoints/competitorformer_scannetpp.pth
```

or:

```bash
huggingface-cli download WangDuanchu/CompetitorFormer competitorformer_scannetpp.pth --local-dir checkpoints
```

```bash
python tools/train.py configs/scannetpp/competitorformer_scannetpp.yaml \
  --work_dir exps/competitorformer_scannetpp \
  --eval_only \
  --resume checkpoints/competitorformer_scannetpp.pth
```

Inference knobs (do not reuse ScanNet v2 values): `num_query=500`, `topk_insts=1300`, `num_class=84`.

### ScanNet v2

- Checkpoint: [`competitorformer_scannet.pth`](https://huggingface.co/WangDuanchu/CompetitorFormer/resolve/main/competitorformer_scannet.pth) (`num_query=400`)

```bash
wget https://huggingface.co/WangDuanchu/CompetitorFormer/resolve/main/competitorformer_scannet.pth \
  -O checkpoints/competitorformer_scannet.pth
```

or:

```bash
huggingface-cli download WangDuanchu/CompetitorFormer competitorformer_scannet.pth --local-dir checkpoints
```

See the [GitHub README](https://github.com/DuanchuWang/CompetitorFormer) for installation, data preparation, training, and evaluation.

## Citation

```bibtex
@InProceedings{Wang_2026_CVPR,
  title     = {CompetitorFormer: Mitigating Query Conflicts for 3D Instance Segmentation via Competitive Strategy},
  author    = {Wang, Duanchu and Yang, Junjie and Gong, Haoran and Liu, Jing and Wang, Di},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  pages     = {34724-34733},
  year      = {2026},
}
```

## License

This project is released under the MIT License.