---
license: apache-2.0
pipeline_tag: image-to-3d
---

# R³: 3D Reconstruction via Relative Regression

R³ is a feed-forward geometry foundation model that reconstructs camera poses and dense geometry from arbitrarily long video streams via relative-pose regression. Instead of regressing every camera in one global frame, R³ predicts confidence-weighted pairwise relative poses on top of a Depth Anything 3 backbone, then assembles a consistent global trajectory downstream.

[**Project Page**](https://kevinxu02.github.io/r3-site/) | [**Paper**](https://huggingface.co/papers/2605.26519) | [**GitHub**](https://github.com/KevinXu02/R3)

## Quick Start

### Installation

```bash
conda env create -f environment.yml
conda activate r3
pip install -e .
```

Alternatively, if you already have a CUDA-enabled PyTorch environment:

```bash
pip install -r requirements.txt
pip install -e .
```

### Run the Demo

You can run inference on a sequence and visualize it using the following command:

```bash
python demo.py --seq_path examples/indoor --no_viewer
```

Presets for common scenarios:

```bash
python demo.py --mode local    # indoor scenes, small coverage
python demo.py --mode long     # long trajectories, large outdoor scenes
python demo.py --mode strided  # temporally strided video
```

## Citation

If R³ is useful in your research or projects, please cite:

```bibtex
@article{r3_2026,
  title  = {R^3: 3D Reconstruction via Relative Regression},
  author = {Anonymous},
  year   = {2026},
  note   = {Paper coming soon}
}
```