20.500.12556/RUL-162586 FICE text-conditioned fashion-image editing with guided GAN inversion Fashion-image editing is a challenging computer-vision task where the goal is to incorporate selected apparel into a given input image. Most existing techniques, known as Virtual Try-On methods, deal with this task by first selecting an example image of the desired apparel and then transferring the clothing onto the target person. Conversely, in this paper, we consider editing fashion images with text descriptions. Such an approach has several advantages over example-based virtual try-on techniques: (i) it does not require an image of the target fashion item, and (ii) it allows the expression of a wide variety of visual concepts through the use of natural language. Existing image-editing methods that work with language inputs are heavily constrained by their requirement for training sets with rich attribute annotations or they are only able to handle simple text descriptions. We address these constraints by proposing a novel text-conditioned editing model called FICE (Fashion Image CLIP Editing) that is capable of handling a wide variety of diverse text descriptions to guide the editing procedure. Specifically, with FICE, we extend the common GAN-inversion process by including semantic, pose-related, and image-level constraints when generating images. We leverage the capabilities of the CLIP model to enforce the text-provided semantics, due to its impressive image–text association capabilities. We furthermore propose a latent-code regularization technique that provides the means to better control the fidelity of the synthesized images. We validate the FICE through rigorous experiments on a combination of VITON images and Fashion-Gen text descriptions and in comparison with several state-of-the-art, text-conditioned, image-editing approaches. Experimental results demonstrate that the FICE generates very realistic fashion images and leads to better editing than existing, competing approaches. The source code is publicly available from: https://github.com/MartinPernus/FICE. text-conditioning GAN inversion image editing generative artificial intelligence generative adversarial networks deep learning multimodality besedilno pogojevanje invertiranje GAN modelov urejanje slik generativna umetna inteligenca true false true Angleški jezik Slovenski jezik Članek v reviji 2024-09-25 12:17:36 2024-09-25 12:17:44 2024-09-29 03:31:35 0000-00-00 00:00:00 2025 0 0 18 str. art. 111022 Vol. 158 2025 0000-00-00 Zaloznikova Objavljeno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.93 0031-3203 10.1016/j.patcog.2024.111022 207863555 1-s2.0-S0031320324007738-main.pdf 1-s2.0-S0031320324007738-main.pdf 1 159EEA326A40F18F0E79952FA1615B4F e3a8744f5dc7ca6b3db92de5d2b160bd27000d8808b170592127d9aec541e42b d07e7e26-7b27-11ef-b232-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=191979 https://www.sciencedirect.com/science/article/pii/S0031320324007738 1 489b8e2e-7b27-11ef-b232-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=191977 Fakulteta za elektrotehniko 0 0 0