| --- |
| license: cc-by-nc-sa-4.0 |
| tags: |
| - 3d-reconstruction |
| - stereo |
| - interactive |
| - 3d |
| - computer-vision |
| - neurips |
| - neurips2026 |
| datasets: |
| - uva-cv-lab/Hard3DBench |
| library_name: pytorch |
| pipeline_tag: image-to-3d |
| --- |
| |
| ## Click3R: Interactive Stereo 3D Reconstruction with Sparse Correspondence Clicks |
|
|
| [](https://uva-computer-vision-lab.github.io/click3r) |
| [](https://huggingface.co/spaces/uva-cv-lab/Click3R) |
| [](https://huggingface.co/datasets/uva-cv-lab/Hard3DBench) |
| [](https://github.com/UVA-Computer-Vision-Lab/click3r) |
|  |
|
|
| Click3R is a framework for interactive geometric correction of feed-forward models using sparse human correspondence clicks. Given an image pair and a small set of cross-view point correspondences provided by a user, Click3R injects geometric constraints into the 3D reconstruction networks through a lightweight point correspondence adapter, enabling the model to resolve ambiguities in challenging scenarios such as repetitive textures, symmetric structures, large viewpoint changes, or textureless regions. |
|
|
| ## Model Zoo |
|
|
| | Model | Description | Link | |
| |-------|-------------|------| |
| | **Click3R** | ViT-L encoder, ViT-B decoder, 566.6M params, 224 × 224. The model of the paper. | [Download](https://huggingface.co/uva-cv-lab/Click3R) | |
| | DUSt3R (retrained) | Same encoder and decoder, 532.3M params, 224 × 224. DUSt3R trained on the same data as Click3R, the baseline of the paper. | [Download](https://huggingface.co/uva-cv-lab/Click3R-DUSt3R-retrained) | |
|
|
| ## Usage |
|
|
| Run the interactive demo. The launcher sets up the environment and downloads the checkpoint: |
| ```bash |
| git clone https://github.com/UVA-Computer-Vision-Lab/click3r |
| cd click3r |
| python demo.py |
| ``` |
|
|
| Download a checkpoint directly: |
| ```bash |
| hf download uva-cv-lab/Click3R click3r.pth --local-dir checkpoints |
| hf download uva-cv-lab/Click3R-DUSt3R-retrained retrained.pth --local-dir checkpoints/dust3r |
| ``` |
|
|
| Evaluation and training commands are in the [code repository](https://github.com/UVA-Computer-Vision-Lab/click3r). |
|
|
| ## Citation |
|
|
| ```bibtex |
| @inproceedings{gu2026click3r, |
| title={Click3R: Interactive Stereo 3D Reconstruction with Sparse Correspondence Clicks}, |
| author={Gu, Hao and Yao, Jin and Cheng, Zezhou}, |
| booktitle={Neural Information Processing Systems (NeurIPS)}, |
| year={2026} |
| } |
| ``` |
|
|
| ## License |
|
|
| The model checkpoints are released under [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/), as they are initialized from CroCo v2 and trained on non-commercial datasets. |
|
|
