Objave

@inproceedings{elmar2026,

title = {CloDe: A Multimodal Tuning-Free Clothing Designer},

author = {Ajda Lampe and Ana Cvetković and Dong Seog Han and Satish Kumar Singh and Vitomir Štruc and Peter Peer},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2026/09/ELMAR_2026___Anac.pdf},

year  = {2026},

date = {2026-08-25},

booktitle = {Proceedings of ELMAR 2026},

pages = {1--4},

abstract = {Recent diffusion-based image generation models have enabled new directions in virtual try-on and garment synthesis. However, existing approaches often trade off between controllability and accessibility: tuning-based methods typically require additional training or specialized inputs, while tuning-free methods may lack structural control and fine-grained appearance guidance. In this work, we propose CloDe, a multimodal, tuning-free garment synthesis framework built on a pretrained diffusion inpainting model. Our method enhances controllability without finetuning the backbone by introducing three components: (i) a category-aware masking strategy that improves edit locality and reduces garment leakage, (ii) pose conditioning via ControlNet to better preserve human structure, and (iii) optional fabric conditioning using IP-Adapter to incorporate fine-grained appearance cues. Built on DiCTI, our approach maintains a fully zero-shot pipeline while improving synthesis quality across realism, pose consistency, and texture fidelity. We evaluate CloDe on VITON-HD using quantitative metrics and a user study, showing consistent improvements over DiCTI in both objective measures and perceptual quality.},

keywords = {CloDE, clothing design, deepbeauty, diffusion models, virtual design, virtual try-on},

pubstate = {published},

tppubtype = {inproceedings}

}