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]ยณ) from human head images.

Input: RGB images of size 512ร—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:

    git clone https://github.com/diddone/densemarks.git
    cd densemarks
    
  2. Install DINOv3 submodule:

    git clone https://github.com/facebookresearch/dinov3 third_party_dinov3
    
  3. Modify DINOv3 for compatibility:

    # For Linux (GNU sed):
    sed -i '/dinov3\.hub\.segmentors/s/^/#/; /dinov3\.hub\.classifiers/s/^/#/; /dinov3\.hub\.detectors/s/^/#/; /dinov3\.hub\.dinotxt/s/^/#/; /dinov3\.hub\.depthers/s/^/#/' third_party_dinov3/hubconf.py
    
    # For macOS (BSD sed):
    sed -i '' '/dinov3\.hub\.segmentors/s/^/#/; /dinov3\.hub\.classifiers/s/^/#/; /dinov3\.hub\.detectors/s/^/#/; /dinov3\.hub\.dinotxt/s/^/#/; /dinov3\.hub\.depthers/s/^/#/' third_party_dinov3/hubconf.py
    
  4. Install dependencies:

    pip install torch transformers numpy
    
  5. Download model weights from Hugging Face:

    from dense_marks_model import DenseMarksModel, read_image
    from huggingface_hub import hf_hub_download
    model = DenseMarksModel(hf_hub_download("diddone/densemarks", "model.safetensors"))
    images = read_image("assets/00000.png") # rgb, 512x512
    uvw = model(images) # Predict UVW coordinates
    
Downloads last month

-

Downloads are not tracked for this model. How to track
Safetensors
Model size
0.1B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support