HybridMQA Checkpoint

This repository hosts the model weights for HybridMQA, a full-reference quality assessment method for 3D colored meshes. HybridMQA leverages both geometry and texture representations and models their interactions to predict perceptual quality scores.

📄 Paper: arXiv:2412.01986
🌐 Project Page: https://arshafiee.github.io/hybridmqa/
💻 Codebase: GitHub Repository

Checkpoints

This repository includes three trained HybridMQA checkpoints:

Filename	Dataset	kfold_seed	shuffle_seed	Notes
`ckpt_TMQA_adapted.pth`	TMQA	27	0	Trained on 80% with the given seeds
`ckpt_TSMD_adapted.pth`	TSMD	7	2	Trained on 80% with the given seeds
`ckpt_YN2023_adapted.pth`	YN2023	7	1	Trained on 80% with the given seeds

Usage

Download the checkpoint using:

from huggingface_hub import hf_hub_download

ckpt_path = hf_hub_download(
    repo_id="arshafiee/hybridmqa-checkpoint",
    filename="<checkpoint_name>.pth"
)

Citation

If you use this work in your research, please cite:

@article{sarvestani2024hybridmqa,
    title={HybridMQA: Exploring Geometry-Texture Interactions for Colored Mesh Quality Assessment},
    author={Sarvestani, Armin Shafiee and Tang, Sheyang and Wang, Zhou},
    journal={arXiv preprint arXiv:2412.01986},
    year={2024}
}

License

This model is released under the MIT License.