Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,93 @@
+---
+license: other
+license_name: sapiens2-license
+license_link: https://github.com/facebookresearch/sapiens2/blob/main/LICENSE.md
+pipeline_tag: depth-estimation
+library_name: sapiens
+base_model: facebook/sapiens2-pretrain-0.8b
+tags:
+  - sapiens
+  - sapiens2
+  - human-centric
+  - pointmap
+---
+
+# Sapiens2-0.8B-Pointmap
+
+Per-pixel 3D pointmap (x, y, z coordinates per pixel in camera frame).
+
+This repository contains the **0.8B Pointmap Estimation** checkpoint, finetuned from the [Sapiens2-0.8B pretrained backbone](https://huggingface.co/facebook/sapiens2-pretrain-0.8b).
+
+- 📄 **Paper:** [OpenReview (ICLR 2026)](https://openreview.net/pdf?id=IVAlYCqdvW)
+- 🌐 **Project Page:** [rawalkhirodkar.github.io/sapiens2](https://rawalkhirodkar.github.io/sapiens2)
+- 💻 **Code:** [github.com/facebookresearch/sapiens2](https://github.com/facebookresearch/sapiens2)
+
+## Model Details
+
+- **Developed by:** Meta
+- **Model type:** Vision Transformer + Pointmap Estimation head
+- **License:** [Sapiens2 License](https://github.com/facebookresearch/sapiens2/blob/main/LICENSE.md)
+- **Task:** pointmap
+- **Base model:** [facebook/sapiens2-pretrain-0.8b](https://huggingface.co/facebook/sapiens2-pretrain-0.8b)
+- **Format:** safetensors
+- **File:** `sapiens2_0.8b_pointmap.safetensors`
+
+## Quick Start
+
+Install the [Sapiens2 repo](https://github.com/facebookresearch/sapiens2) (`pip install -e .`), download the checkpoint, and run the demo:
+
+```bash
+# 1. Download the checkpoint to $SAPIENS_CHECKPOINT_ROOT/pointmap/
+hf download facebook/sapiens2-pointmap-0.8b sapiens2_0.8b_pointmap.safetensors \
+    --local-dir ~/sapiens2_host/pointmap
+
+# 2. Run the demo (edit INPUT, OUTPUT, and MODEL_NAME inside the script)
+cd $SAPIENS_ROOT/sapiens/dense
+./scripts/demo/pointmap.sh
+```
+
+See the [Pointmap Estimation guide](https://github.com/facebookresearch/sapiens2/blob/main/docs/POINTMAP.md) for details on inputs, outputs, and visualization options.
+
+## Model Card
+
+| Field | Value |
+|-------|-------|
+| Architecture | Sapiens2 ViT backbone + Pointmap Estimation head |
+| Backbone parameters | 0.818 B |
+| Backbone FLOPs | 2.592 T |
+| Embedding dim | 1280 |
+| Layers | 32 |
+| Attention heads | 16 |
+| Inference resolution | 1024 × 768 (H × W) |
+| Patch size | 16 |
+
+### Sapiens2-Pointmap Family
+
+| Model | Params | FLOPs | Embed dim | Layers | Heads |
+|-------|--------|-------|-----------|--------|-------|
+| [Sapiens2-0.4B](https://huggingface.co/facebook/sapiens2-pointmap-0.4b) | 0.398 B | 1.260 T | 1024 | 24 | 16 |
+| **Sapiens2-0.8B** *(this)* | 0.818 B | 2.592 T | 1280 | 32 | 16 |
+| [Sapiens2-1B](https://huggingface.co/facebook/sapiens2-pointmap-1b) | 1.462 B | 4.715 T | 1536 | 40 | 24 |
+| [Sapiens2-5B](https://huggingface.co/facebook/sapiens2-pointmap-5b) | 5.071 B | 15.722 T | 2432 | 56 | 32 |
+
+See the [Sapiens2 Collection](https://huggingface.co/collections/facebook/sapiens2) for all variants and other downstream task checkpoints.
+
+## Intended Use
+
+- Pointmap Estimation on human-centric imagery
+- Research on human-centric vision
+
+## License
+
+Released under the [Sapiens2 License](https://github.com/facebookresearch/sapiens2/blob/main/LICENSE.md).
+
+## Citation
+
+```bibtex
+@inproceedings{khirodkar2026sapiens2,
+  title={Sapiens2},
+  author={Khirodkar, Rawal and Wen, He and Martinez, Julieta and Dong, Yuan and Zhaoen, Su and Saito, Shunsuke},
+  booktitle={International Conference on Learning Representations (ICLR)},
+  year={2026}
+}
+```