Add model card for DA-Next

README.md

@@ -0,0 +1,43 @@
+---
+license: cc-by-4.0
+pipeline_tag: depth-estimation
+---
+
+# DA-Next
+
+DA-Next is a metric-scale spatial foundation model introduced as a baseline in the paper [SpatialBench: Is Your Spatial Foundation Model an All-Round Player?](https://huggingface.co/papers/2605.27367). 
+
+It is a metric-scale extension of [Depth Anything 3](https://github.com/ByteDance-Seed/Depth-Anything-3) that adds a scale head, a camera encoder, and ray-based pose decoding to improve spatial representation learning.
+
+- **Paper:** [SpatialBench: Is Your Spatial Foundation Model an All-Round Player?](https://huggingface.co/papers/2605.27367)
+- **Project Page:** [https://ropedia.github.io/SpatialBench/](https://ropedia.github.io/SpatialBench/)
+- **Repository:** [https://github.com/Ropedia/SpatialBench](https://github.com/Ropedia/SpatialBench)
+
+## Usage
+
+You can evaluate DA-Next via the unified harness provided in the SpatialBench repository:
+
+```bash
+# Fetch the DA-Next submodule (one-time)
+git submodule update --init --recursive DA-Next
+
+# Evaluate DA-Next via the unified harness
+python benchmark/evaluation/run_benchmark.py \
+    --config benchmark/configs/end2end/danext_eval.yaml
+```
+
+## Citation
+
+If DA-Next or SpatialBench is useful for your research, please cite:
+
+```bibtex
+@misc{peng2026spatialbench,
+      title={SpatialBench: Is Your Spatial Foundation Model an All-Round Player?}, 
+      author={Haosong Peng and Hao Li and Jiaqi Chen and Yuhao Pan and Runmao Yao and Yalun Dai and Fushuo Huo and Fangzhou Hong and Zhaoxi Chen and Haozhao Wang and Dingwen Zhang and Ziwei Liu and Wenchao Xu},
+      year={2026},
+      eprint={2605.27367},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2605.27367}, 
+}
+```