Add model card

README.md

@@ -0,0 +1,62 @@
+---
+license: other
+license_name: prl-1.0
+license_link: https://github.com/zju3dv/UniVerse/blob/main/LICENSE
+tags:
+- video-diffusion
+- image-restoration
+- 3d-reconstruction
+- nerf
+---
+
+# UniVerse checkpoints
+
+Weights of the video diffusion model of **UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance
+Field Reconstruction** (ICCV 2025).
+
+[Code](https://github.com/zju3dv/UniVerse) | [Paper](https://arxiv.org/abs/2510.01669) |
+[Project Page](https://jin-cao-tma.github.io/UniVerse.github.io/)
+
+| File | Model | Resolution | Training | sha256 |
+|---|---|---|---|---|
+| `universe_512.ckpt` | UniVerse-512 | 320 x 512 | stage 1, 14,520 iterations | `7c86adcd48bb32054d62e4bb47831014b5e9c481f2cea028dfb429e08547bdea` |
+
+The file is a weights-only PyTorch Lightning checkpoint (fp32, 10.4 GB) that contains the whole model,
+including the VAE and the OpenCLIP ViT-H/14 encoders.
+
+## Usage
+
+In the [GitHub repository](https://github.com/zju3dv/UniVerse), `inference.py` downloads the
+checkpoint into `checkpoints/` on first use:
+
+```bash
+python inference.py --image_dir data/demo/images --out_dir output/demo
+```
+
+or download it manually:
+
+```bash
+hf download TmaKiss/UniVerse universe_512.ckpt --local-dir checkpoints
+```
+
+## Terms
+
+The models are fine-tuned from ViewCrafter's `ViewCrafter_25_sparse` (Apache-2.0), contain the OpenCLIP
+ViT-H/14 weights trained on LAION-2B (MIT), and were trained on
+[DL3DV-10K](https://github.com/DL3DV-10K/Dataset), which is released for non-commercial use
+(CC BY-NC 4.0). The UniVerse release is distributed under the ZJU3DV Project Registration License
+(PRL) v1.0, see the repository's [LICENSE](https://github.com/zju3dv/UniVerse/blob/main/LICENSE).
+
+## Citation
+
+```bibtex
+@misc{cao2025universeunleashingsceneprior,
+  title={UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance Field Reconstruction},
+  author={Jin Cao and Hongrui Wu and Ziyong Feng and Hujun Bao and Xiaowei Zhou and Sida Peng},
+  year={2025},
+  eprint={2510.01669},
+  archivePrefix={arXiv},
+  primaryClass={cs.CV},
+  url={https://arxiv.org/abs/2510.01669},
+}
+```