You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

S23DR2026

Setup

virtualenv venv
source venv/bin/activate
pip install -r requirements.txt

Scripts

Run wireframe prediction and visualize results in Rerun:

python eval.py --split validation --method METHOD --visualize

Methods to choose from:

  • 'empty': Empty solution.
  • 'handcrafted': Baseline from workshop organizers.
  • 'v1': Identify edges in segmenation images and lift to 3D using refined depthmaps.

Challenge submission

Make sure that the submission script (script.py) is updated to run the right method.

Upload the code to our Hugging Face model:

./upload_to_hf.sh

Go to the challenge website, press New submission, enter "ghanning/S23DR2026", click Submit.

Useful links

https://usm3d.github.io/ (workshop webpage)

https://huggingface.co/spaces/usm3d/S23DR2026 (2026 challenge)

https://huggingface.co/datasets/usm3d/hoho22k_2026_trainval (dataset webpage)

https://github.com/s23dr/hoho2025 (tools & utilities)

https://github.com/s23dr/wireframe-metrics-iccv2025

https://huggingface.co/spaces/usm3d/S23DR2025 (2025 challenge)

https://huggingface.co/datasets/usm3d/hoho25k (2025 dataset webpage)

https://huggingface.co/jskvrna/hoho (2025 challenge winner)

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support