docs: add paper metadata, quickstart, and citation

README.md

@@ -20,6 +20,8 @@ Please note: For individuals or organizations generating annual revenue of US $1
 
 * **Developed by**: [Stability AI](https://stability.ai/)
 * **Model type**: Transformer multi-view image-to-3D model
+* **Paper**: [ReLi3D: Relightable Multi-view 3D Reconstruction with Disentangled Illumination](https://arxiv.org/abs/2603.19753)
+* **Authors**: Jan-Niklas Dihlmann, Mark Boss, Simon Donne, Andreas Engelhardt, Hendrik P. A. Lensch, Varun Jampani
 * **Model details**: ReLi3D is trained to reconstruct a relightable 3D mesh from multiple 512x512 object images with known camera poses. The model outputs UV-unwrapped geometry and texture, and predicts material properties such as roughness and metallic values, together with an estimated illumination representation for downstream rendering workflows.
 
 ### License
@@ -30,7 +32,7 @@ Please note: For individuals or organizations generating annual revenue of US $1
 
 * **Repository**: https://github.com/Stability-AI/ReLi3D
 * **Project page**: https://reli3d.jdihlmann.com/
-* **arXiv page**: Coming soon
+* **arXiv paper**: https://arxiv.org/abs/2603.19753
 
 ### Files
 
@@ -41,9 +43,31 @@ Please note: For individuals or organizations generating annual revenue of US $1
 
 The training process uses renders from Objaverse and curated subsets of additional sources with license review and filtering for training suitability.
 
-## Usage
+## Quickstart
 
-For usage instructions, please refer to the [ReLi3D GitHub repository](https://github.com/Stability-AI/ReLi3D).
+```bash
+git clone https://github.com/Stability-AI/ReLi3D.git
+cd ReLi3D
+
+python3.10 -m venv .venv
+source .venv/bin/activate
+pip install --upgrade pip
+pip install -r requirements.txt
+pip install ./native/uv_unwrapper ./native/texture_baker
+
+huggingface-cli login
+python scripts/download_model_from_hf.py \
+  --repo-id StabilityLabs/ReLi3D \
+  --output-dir artifacts/model
+
+python demos/reli3d/infer_from_transforms.py \
+  --input-root demo_files/objects \
+  --objects Camera_01 \
+  --output-root outputs \
+  --overwrite
+```
+
+For full usage instructions, please refer to the [ReLi3D GitHub repository](https://github.com/Stability-AI/ReLi3D).
 
 ### Intended Uses
 
@@ -59,6 +83,17 @@ All uses of the model should be in accordance with our [Acceptable Use Policy](h
 
 The model was not trained to be factual or true representations of people or events. As such, using the model to generate such content is out-of-scope of the abilities of this model.
 
+## Citation
+
+```bibtex
+@inproceeding{dihlmann2026reli3d,
+  author = {Dihlmann, Jan-Niklas and Boss, Mark and Donne, Simon and Engelhardt, Andreas and Lensch, Hendrik P. A. and Jampani, Varun},
+  title = {ReLi3D: Relightable Multi-view 3D Reconstruction with Disentangled Illumination},
+  booktitle = {International Conference on Learning Representations (ICLR)},
+  year = {2026}
+}
+```
+
 ## Safety
 
 As part of our safety-by-design and responsible AI deployment approach, we implement safety measures throughout the development of our models, from the time we begin pre-training a model to the ongoing development, fine-tuning, and deployment of each model. We have implemented a number of safety mitigations that are intended to reduce the risk of severe harms. However, we recommend that developers conduct their own testing and apply additional mitigations based on their specific use cases.