Upload README.md with huggingface_hub

README.md

@@ -1,3 +1,46 @@
----
-license: cc-by-nc-4.0
----
+# DenseMarks
+
+A PyTorch implementation for dense UVW coordinate prediction from human head images using DINOv3 backbone with DPT head architecture.
+
+## Overview
+
+DenseMarks predicts per-pixel positions in canonical space (cube [0, 1]³) from human head images.
+
+**Input**: RGB images of size 512×512 pixels
+
+**Output**: UVW coordinates tensor (B, 3, 512, 512) with values in [0, 1]
+
+## Prerequisites
+
+- Python 3.8+
+- PyTorch 1.12+
+- CUDA (optional, for GPU acceleration)
+
+## Installation
+
+1. **Clone the repository:**
+   ```bash
+   git clone https://github.com/yourusername/densemarks.git
+   cd densemarks
+   ```
+
+2. **Install DINOv3 submodule:**
+   ```bash
+   git clone https://github.com/facebookresearch/dinov3 third_party_dinov3
+   ```
+
+3. **Modify DINOv3 for compatibility:**
+   ```bash
+   sed -i '/dinov3\.hub\.segmentors/s/^/#/' third_party_dinov3/hubconf.py
+   ```
+
+4. **Install dependencies:**
+   ```bash
+   pip install torch transformers numpy
+   ```
+
+5. **Download model weights from Hugging Face:**
+   ```bash
+   # Download model_final.pth from Hugging Face Hub
+   # Place it in the repository root
+   ```