2026 |
Lampe, Ajda; Cvetković, Ana; Han, Dong Seog; Singh, Satish Kumar; Štruc, Vitomir; Peer, Peter CloDe: A Multimodal Tuning-Free Clothing Designer Proceedings Article In: Proceedings of ELMAR 2026, pp. 1–4, 2026. Abstract | Links | BibTeX | Tags: CloDE, clothing design, deepbeauty, diffusion models, virtual design, virtual try-on @inproceedings{elmar2026,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. |
2024 |
Lampe, Ajda; Stopar, Julija; Jain, Deepak Kumar; Omachi, Shinichiro; Peer, Peter; Struc, Vitomir DiCTI: Diffusion-based Clothing Designer via Text-guided Input Proceedings Article In: Proceedings of the18th International Conference on Automatic Face and Gesture Recognition (FG 2024), pp. 1-9, 2024. Abstract | Links | BibTeX | Tags: clothing design, deepbeauty, denoising diffusion probabilistic models, diffusion, diffusion models, fashion, virtual try-on @inproceedings{Ajda_Dicti,Recent developments in deep generative models have opened up a wide range of opportunities for image synthesis, leading to significant changes in various creative fields, including the fashion industry. While numerous methods have been proposed to benefit buyers, particularly in virtual try-on applications, there has been relatively less focus on facilitating fast prototyping for designers and customers seeking to order new designs. To address this gap, we introduce DiCTI (Diffusion-based Clothing Designer via Text-guided Input), a straightforward yet highly effective approach that allows designers to quickly visualize fashion-related ideas using text inputs only. Given an image of a person and a description of the desired garments as input, DiCTI automatically generates multiple high-resolution, photorealistic images that capture the expressed semantics. By leveraging a powerful diffusion-based inpainting model conditioned on text inputs, DiCTI is able to synthesize convincing, high-quality images with varied clothing designs that viably follow the provided text descriptions, while being able to process very diverse and challenging inputs, captured in completely unconstrained settings. We evaluate DiCTI in comprehensive experiments on two different datasets (VITON-HD and Fashionpedia) and in comparison to the state-of-the-art (SoTa). The results of our experiments show that DiCTI convincingly outperforms the SoTA competitor in generating higher quality images with more elaborate garments and superior text prompt adherence, both according to standard quantitative evaluation measures and human ratings, generated as part of a user study. The source code of DiCTI will be made publicly available. |
Ivanovska, Marija; Štruc, Vitomir On the Vulnerability of Deepfake Detectors to Attacks Generated by Denoising Diffusion Models Proceedings Article In: Proceedings of WACV Workshops, pp. 1051-1060, 2024. Abstract | Links | BibTeX | Tags: deep learning, deepfake, deepfake detection, diffusion models, face, media forensics @inproceedings{MarijaWACV24,The detection of malicious deepfakes is a constantly evolving problem that requires continuous monitoring of detectors to ensure they can detect image manipulations generated by the latest emerging models. In this paper, we investigate the vulnerability of single–image deepfake detectors to black–box attacks created by the newest generation of generative methods, namely Denoising Diffusion Models (DDMs). Our experiments are run on FaceForensics++, a widely used deepfake benchmark consisting of manipulated images generated with various techniques for face identity swapping and face reenactment. Attacks are crafted through guided reconstruction of existing deepfakes with a proposed DDM approach for face restoration. Our findings indicate that employing just a single denoising diffusion step in the reconstruction process of a deepfake can significantly reduce the likelihood of detection, all without introducing any perceptible image modifications. While training detectors using attack examples demonstrated some effectiveness, it was observed that discriminators trained on fully diffusion–based deepfakes exhibited limited generalizability when presented with our attacks. |